$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-9B-GGUF\snapshots\3885219b6810b007914f3a7950a8d1b469d598a5\Qwen3.5-9B-Q6_K.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.109.942 I srv llama_server: initializing ... 0.00.109.948 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.110.060 I srv init_listene: The UI is disabled 0.00.110.062 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.110.138 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.116.806 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-9B-GGUF\snapshots\3885219b6810b007914f3a7950a8d1b469d598a5\Qwen3.5-9B-Q6_K.gguf' 0.03.348.756 I cmn init: llama threadpool init, n_threads = 8 0.03.428.818 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.03.433.555 I srv llama_server: model loaded 0.03.433.561 I srv llama_server: listening on http://127.0.0.1:8089 0.04.570.327 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.570.473 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.234.077 I slot print_timing: id 0 | task 0 | prompt eval time = 160.45 ms / 368 tokens ( 0.44 ms per token, 2293.52 tokens per second) 0.05.234.083 I slot print_timing: id 0 | task 0 | eval time = 503.13 ms / 41 tokens ( 12.58 ms per token, 79.50 tokens per second) 0.05.234.084 I slot print_timing: id 0 | task 0 | total time = 663.59 ms / 409 tokens 0.05.234.090 I slot print_timing: id 0 | task 0 | graphs reused = 40 0.05.234.090 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.234.117 I slot release: id 0 | task 0 | stop processing: n_tokens = 408, truncated = 0 0.05.253.140 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 5126166 0.05.279.571 I slot launch_slot_: id 0 | task 44 | processing task, is_child = 0 0.05.928.497 I slot print_timing: id 0 | task 44 | prompt eval time = 137.56 ms / 322 tokens ( 0.43 ms per token, 2340.85 tokens per second) 0.05.928.503 I slot print_timing: id 0 | task 44 | eval time = 511.35 ms / 42 tokens ( 12.47 ms per token, 80.18 tokens per second) 0.05.928.504 I slot print_timing: id 0 | task 44 | total time = 648.91 ms / 364 tokens 0.05.928.504 I slot print_timing: id 0 | task 44 | graphs reused = 80 0.05.928.505 I slot print_timing: id 0 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.928.530 I slot release: id 0 | task 44 | stop processing: n_tokens = 363, truncated = 0 0.05.951.521 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 5820579 0.05.977.326 I slot launch_slot_: id 0 | task 89 | processing task, is_child = 0 0.06.628.579 I slot print_timing: id 0 | task 89 | prompt eval time = 139.93 ms / 365 tokens ( 0.38 ms per token, 2608.48 tokens per second) 0.06.628.585 I slot print_timing: id 0 | task 89 | eval time = 511.31 ms / 42 tokens ( 12.47 ms per token, 80.19 tokens per second) 0.06.628.585 I slot print_timing: id 0 | task 89 | total time = 651.23 ms / 407 tokens 0.06.628.586 I slot print_timing: id 0 | task 89 | graphs reused = 120 0.06.628.587 I slot print_timing: id 0 | task 89 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.628.614 I slot release: id 0 | task 89 | stop processing: n_tokens = 406, truncated = 0 0.06.648.009 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 6520663 0.06.674.356 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 0.07.346.385 I slot print_timing: id 0 | task 134 | prompt eval time = 148.59 ms / 397 tokens ( 0.37 ms per token, 2671.85 tokens per second) 0.07.346.391 I slot print_timing: id 0 | task 134 | eval time = 523.42 ms / 43 tokens ( 12.46 ms per token, 80.24 tokens per second) 0.07.346.392 I slot print_timing: id 0 | task 134 | total time = 672.01 ms / 440 tokens 0.07.346.393 I slot print_timing: id 0 | task 134 | graphs reused = 161 0.07.346.394 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.346.422 I slot release: id 0 | task 134 | stop processing: n_tokens = 439, truncated = 0 0.07.368.341 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.103 0.07.393.819 I slot launch_slot_: id 0 | task 180 | processing task, is_child = 0 0.08.209.070 I slot print_timing: id 0 | task 180 | prompt eval time = 142.96 ms / 383 tokens ( 0.37 ms per token, 2679.16 tokens per second) 0.08.209.076 I slot print_timing: id 0 | task 180 | eval time = 672.28 ms / 55 tokens ( 12.45 ms per token, 80.32 tokens per second) 0.08.209.077 I slot print_timing: id 0 | task 180 | total time = 815.23 ms / 438 tokens 0.08.209.078 I slot print_timing: id 0 | task 180 | graphs reused = 214 0.08.209.079 I slot print_timing: id 0 | task 180 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.209.106 I slot release: id 0 | task 180 | stop processing: n_tokens = 437, truncated = 0 0.08.212.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 8101155 0.08.238.398 I slot launch_slot_: id 0 | task 238 | processing task, is_child = 0 0.09.057.383 I slot print_timing: id 0 | task 238 | prompt eval time = 146.61 ms / 372 tokens ( 0.39 ms per token, 2537.31 tokens per second) 0.09.057.389 I slot print_timing: id 0 | task 238 | eval time = 672.35 ms / 55 tokens ( 12.45 ms per token, 80.31 tokens per second) 0.09.057.390 I slot print_timing: id 0 | task 238 | total time = 818.96 ms / 427 tokens 0.09.057.391 I slot print_timing: id 0 | task 238 | graphs reused = 267 0.09.057.391 I slot print_timing: id 0 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.057.419 I slot release: id 0 | task 238 | stop processing: n_tokens = 426, truncated = 0 0.09.081.642 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 8949468 0.09.106.889 I slot launch_slot_: id 0 | task 296 | processing task, is_child = 0 0.09.944.086 I slot print_timing: id 0 | task 296 | prompt eval time = 165.27 ms / 422 tokens ( 0.39 ms per token, 2553.37 tokens per second) 0.09.944.091 I slot print_timing: id 0 | task 296 | eval time = 671.90 ms / 55 tokens ( 12.44 ms per token, 80.37 tokens per second) 0.09.944.092 I slot print_timing: id 0 | task 296 | total time = 837.18 ms / 477 tokens 0.09.944.093 I slot print_timing: id 0 | task 296 | graphs reused = 320 0.09.944.094 I slot print_timing: id 0 | task 296 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.944.122 I slot release: id 0 | task 296 | stop processing: n_tokens = 476, truncated = 0 0.09.971.361 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 9836171 0.09.997.132 I slot launch_slot_: id 0 | task 354 | processing task, is_child = 0 0.11.053.247 I slot print_timing: id 0 | task 354 | prompt eval time = 169.78 ms / 470 tokens ( 0.36 ms per token, 2768.34 tokens per second) 0.11.053.253 I slot print_timing: id 0 | task 354 | eval time = 886.32 ms / 72 tokens ( 12.48 ms per token, 80.11 tokens per second) 0.11.053.255 I slot print_timing: id 0 | task 354 | total time = 1056.10 ms / 542 tokens 0.11.053.256 I slot print_timing: id 0 | task 354 | graphs reused = 389 0.11.053.257 I slot print_timing: id 0 | task 354 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.053.287 I slot release: id 0 | task 354 | stop processing: n_tokens = 541, truncated = 0 0.11.076.820 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 10945336 0.11.102.833 I slot launch_slot_: id 0 | task 429 | processing task, is_child = 0 0.11.815.784 I slot print_timing: id 0 | task 429 | prompt eval time = 139.79 ms / 345 tokens ( 0.41 ms per token, 2467.97 tokens per second) 0.11.815.789 I slot print_timing: id 0 | task 429 | eval time = 573.14 ms / 47 tokens ( 12.46 ms per token, 80.26 tokens per second) 0.11.815.790 I slot print_timing: id 0 | task 429 | total time = 712.93 ms / 392 tokens 0.11.815.791 I slot print_timing: id 0 | task 429 | graphs reused = 434 0.11.815.792 I slot print_timing: id 0 | task 429 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.815.819 I slot release: id 0 | task 429 | stop processing: n_tokens = 391, truncated = 0 0.11.843.522 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 11707868 0.11.868.681 I slot launch_slot_: id 0 | task 479 | processing task, is_child = 0 0.12.508.974 I slot print_timing: id 0 | task 479 | prompt eval time = 140.19 ms / 364 tokens ( 0.39 ms per token, 2596.42 tokens per second) 0.12.508.980 I slot print_timing: id 0 | task 479 | eval time = 500.08 ms / 41 tokens ( 12.50 ms per token, 79.99 tokens per second) 0.12.508.980 I slot print_timing: id 0 | task 479 | total time = 640.27 ms / 405 tokens 0.12.508.981 I slot print_timing: id 0 | task 479 | graphs reused = 473 0.12.508.982 I slot print_timing: id 0 | task 479 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.509.008 I slot release: id 0 | task 479 | stop processing: n_tokens = 404, truncated = 0 0.12.527.299 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 12401057 0.12.552.899 I slot launch_slot_: id 0 | task 523 | processing task, is_child = 0 0.13.489.503 I slot print_timing: id 0 | task 523 | prompt eval time = 146.66 ms / 376 tokens ( 0.39 ms per token, 2563.68 tokens per second) 0.13.489.510 I slot print_timing: id 0 | task 523 | eval time = 789.92 ms / 62 tokens ( 12.95 ms per token, 77.22 tokens per second) 0.13.489.511 I slot print_timing: id 0 | task 523 | total time = 936.58 ms / 438 tokens 0.13.489.512 I slot print_timing: id 0 | task 523 | graphs reused = 533 0.13.489.513 I slot print_timing: id 0 | task 523 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.489.543 I slot release: id 0 | task 523 | stop processing: n_tokens = 437, truncated = 0 0.13.511.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 13381592 0.13.536.782 I slot launch_slot_: id 0 | task 588 | processing task, is_child = 0 0.14.264.610 I slot print_timing: id 0 | task 588 | prompt eval time = 148.94 ms / 412 tokens ( 0.36 ms per token, 2766.16 tokens per second) 0.14.264.618 I slot print_timing: id 0 | task 588 | eval time = 578.86 ms / 47 tokens ( 12.58 ms per token, 79.47 tokens per second) 0.14.264.620 I slot print_timing: id 0 | task 588 | total time = 727.80 ms / 459 tokens 0.14.264.622 I slot print_timing: id 0 | task 588 | graphs reused = 578 0.14.264.624 I slot print_timing: id 0 | task 588 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.264.675 I slot release: id 0 | task 588 | stop processing: n_tokens = 458, truncated = 0 0.14.269.756 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 14156724 0.14.303.153 I slot launch_slot_: id 0 | task 638 | processing task, is_child = 0 0.15.227.418 I slot print_timing: id 0 | task 638 | prompt eval time = 148.46 ms / 376 tokens ( 0.39 ms per token, 2532.70 tokens per second) 0.15.227.424 I slot print_timing: id 0 | task 638 | eval time = 775.78 ms / 62 tokens ( 12.72 ms per token, 78.63 tokens per second) 0.15.227.425 I slot print_timing: id 0 | task 638 | total time = 924.24 ms / 438 tokens 0.15.227.426 I slot print_timing: id 0 | task 638 | graphs reused = 638 0.15.227.426 I slot print_timing: id 0 | task 638 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.227.453 I slot release: id 0 | task 638 | stop processing: n_tokens = 437, truncated = 0 0.15.231.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 15119502 0.15.257.331 I slot launch_slot_: id 0 | task 703 | processing task, is_child = 0 0.16.040.772 I slot print_timing: id 0 | task 703 | prompt eval time = 147.31 ms / 378 tokens ( 0.39 ms per token, 2566.00 tokens per second) 0.16.040.778 I slot print_timing: id 0 | task 703 | eval time = 636.11 ms / 52 tokens ( 12.47 ms per token, 80.17 tokens per second) 0.16.040.779 I slot print_timing: id 0 | task 703 | total time = 783.42 ms / 430 tokens 0.16.040.780 I slot print_timing: id 0 | task 703 | graphs reused = 688 0.16.040.781 I slot print_timing: id 0 | task 703 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.040.809 I slot release: id 0 | task 703 | stop processing: n_tokens = 429, truncated = 0 0.16.066.920 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 15932857 0.16.092.437 I slot launch_slot_: id 0 | task 758 | processing task, is_child = 0 0.16.981.337 I slot print_timing: id 0 | task 758 | prompt eval time = 147.10 ms / 367 tokens ( 0.40 ms per token, 2494.88 tokens per second) 0.16.981.343 I slot print_timing: id 0 | task 758 | eval time = 741.78 ms / 58 tokens ( 13.01 ms per token, 76.84 tokens per second) 0.16.981.344 I slot print_timing: id 0 | task 758 | total time = 888.88 ms / 425 tokens 0.16.981.345 I slot print_timing: id 0 | task 758 | graphs reused = 744 0.16.981.346 I slot print_timing: id 0 | task 758 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.981.374 I slot release: id 0 | task 758 | stop processing: n_tokens = 424, truncated = 0 0.16.998.211 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 16873423 0.17.023.594 I slot launch_slot_: id 0 | task 819 | processing task, is_child = 0 0.17.786.454 I slot print_timing: id 0 | task 819 | prompt eval time = 139.21 ms / 347 tokens ( 0.40 ms per token, 2492.65 tokens per second) 0.17.786.460 I slot print_timing: id 0 | task 819 | eval time = 623.63 ms / 51 tokens ( 12.47 ms per token, 80.18 tokens per second) 0.17.786.462 I slot print_timing: id 0 | task 819 | total time = 762.84 ms / 398 tokens 0.17.786.463 I slot print_timing: id 0 | task 819 | graphs reused = 793 0.17.786.464 I slot print_timing: id 0 | task 819 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.786.493 I slot release: id 0 | task 819 | stop processing: n_tokens = 397, truncated = 0 0.17.809.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 17678542 0.17.834.305 I slot launch_slot_: id 0 | task 873 | processing task, is_child = 0 0.18.473.834 I slot print_timing: id 0 | task 873 | prompt eval time = 139.46 ms / 369 tokens ( 0.38 ms per token, 2645.86 tokens per second) 0.18.473.840 I slot print_timing: id 0 | task 873 | eval time = 500.05 ms / 41 tokens ( 12.50 ms per token, 79.99 tokens per second) 0.18.473.841 I slot print_timing: id 0 | task 873 | total time = 639.51 ms / 410 tokens 0.18.473.842 I slot print_timing: id 0 | task 873 | graphs reused = 832 0.18.473.843 I slot print_timing: id 0 | task 873 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.473.868 I slot release: id 0 | task 873 | stop processing: n_tokens = 409, truncated = 0 0.18.494.362 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 18365917 0.18.519.725 I slot launch_slot_: id 0 | task 917 | processing task, is_child = 0 0.19.157.724 I slot print_timing: id 0 | task 917 | prompt eval time = 138.75 ms / 352 tokens ( 0.39 ms per token, 2536.92 tokens per second) 0.19.157.730 I slot print_timing: id 0 | task 917 | eval time = 499.23 ms / 41 tokens ( 12.48 ms per token, 80.12 tokens per second) 0.19.157.731 I slot print_timing: id 0 | task 917 | total time = 637.98 ms / 393 tokens 0.19.157.732 I slot print_timing: id 0 | task 917 | graphs reused = 871 0.19.157.734 I slot print_timing: id 0 | task 917 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.157.762 I slot release: id 0 | task 917 | stop processing: n_tokens = 392, truncated = 0 0.19.174.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 19049811 0.19.200.646 I slot launch_slot_: id 0 | task 961 | processing task, is_child = 0 0.19.826.987 I slot print_timing: id 0 | task 961 | prompt eval time = 139.41 ms / 349 tokens ( 0.40 ms per token, 2503.50 tokens per second) 0.19.826.993 I slot print_timing: id 0 | task 961 | eval time = 486.92 ms / 40 tokens ( 12.49 ms per token, 80.10 tokens per second) 0.19.826.994 I slot print_timing: id 0 | task 961 | total time = 626.32 ms / 389 tokens 0.19.826.994 I slot print_timing: id 0 | task 961 | graphs reused = 909 0.19.826.995 I slot print_timing: id 0 | task 961 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.827.022 I slot release: id 0 | task 961 | stop processing: n_tokens = 388, truncated = 0 0.19.853.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 19719071 0.19.878.721 I slot launch_slot_: id 0 | task 1004 | processing task, is_child = 0 0.20.830.595 I slot print_timing: id 0 | task 1004 | prompt eval time = 149.36 ms / 384 tokens ( 0.39 ms per token, 2570.94 tokens per second) 0.20.830.601 I slot print_timing: id 0 | task 1004 | eval time = 802.49 ms / 63 tokens ( 12.94 ms per token, 77.26 tokens per second) 0.20.830.602 I slot print_timing: id 0 | task 1004 | total time = 951.85 ms / 447 tokens 0.20.830.603 I slot print_timing: id 0 | task 1004 | graphs reused = 970 0.20.830.604 I slot print_timing: id 0 | task 1004 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.830.635 I slot release: id 0 | task 1004 | stop processing: n_tokens = 446, truncated = 0 0.20.849.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 20722684 0.20.875.586 I slot launch_slot_: id 0 | task 1070 | processing task, is_child = 0 0.21.675.832 I slot print_timing: id 0 | task 1070 | prompt eval time = 139.21 ms / 356 tokens ( 0.39 ms per token, 2557.29 tokens per second) 0.21.675.838 I slot print_timing: id 0 | task 1070 | eval time = 661.02 ms / 54 tokens ( 12.47 ms per token, 80.18 tokens per second) 0.21.675.839 I slot print_timing: id 0 | task 1070 | total time = 800.23 ms / 410 tokens 0.21.675.839 I slot print_timing: id 0 | task 1070 | graphs reused = 1022 0.21.675.840 I slot print_timing: id 0 | task 1070 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.675.867 I slot release: id 0 | task 1070 | stop processing: n_tokens = 409, truncated = 0 0.21.692.376 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 21567916 0.21.719.775 I slot launch_slot_: id 0 | task 1127 | processing task, is_child = 0 0.22.727.874 I slot print_timing: id 0 | task 1127 | prompt eval time = 149.82 ms / 410 tokens ( 0.37 ms per token, 2736.62 tokens per second) 0.22.727.880 I slot print_timing: id 0 | task 1127 | eval time = 858.26 ms / 70 tokens ( 12.44 ms per token, 80.40 tokens per second) 0.22.727.881 I slot print_timing: id 0 | task 1127 | total time = 1008.08 ms / 480 tokens 0.22.727.881 I slot print_timing: id 0 | task 1127 | graphs reused = 1090 0.22.727.882 I slot print_timing: id 0 | task 1127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.727.910 I slot release: id 0 | task 1127 | stop processing: n_tokens = 479, truncated = 0 0.22.749.758 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 22619959 0.22.775.461 I slot launch_slot_: id 0 | task 1200 | processing task, is_child = 0 0.23.634.441 I slot print_timing: id 0 | task 1200 | prompt eval time = 148.34 ms / 385 tokens ( 0.39 ms per token, 2595.42 tokens per second) 0.23.634.446 I slot print_timing: id 0 | task 1200 | eval time = 710.62 ms / 58 tokens ( 12.47 ms per token, 80.21 tokens per second) 0.23.634.448 I slot print_timing: id 0 | task 1200 | total time = 858.96 ms / 443 tokens 0.23.634.449 I slot print_timing: id 0 | task 1200 | graphs reused = 1146 0.23.634.449 I slot print_timing: id 0 | task 1200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.634.478 I slot release: id 0 | task 1200 | stop processing: n_tokens = 442, truncated = 0 0.23.649.995 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 23526527 0.23.675.638 I slot launch_slot_: id 0 | task 1261 | processing task, is_child = 0 0.24.699.343 I slot print_timing: id 0 | task 1261 | prompt eval time = 150.80 ms / 395 tokens ( 0.38 ms per token, 2619.42 tokens per second) 0.24.699.348 I slot print_timing: id 0 | task 1261 | eval time = 872.88 ms / 71 tokens ( 12.47 ms per token, 80.19 tokens per second) 0.24.699.350 I slot print_timing: id 0 | task 1261 | total time = 1023.68 ms / 466 tokens 0.24.699.350 I slot print_timing: id 0 | task 1261 | graphs reused = 1215 0.24.699.351 I slot print_timing: id 0 | task 1261 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.699.387 I slot release: id 0 | task 1261 | stop processing: n_tokens = 465, truncated = 0 0.24.723.694 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 24591436 0.24.750.412 I slot launch_slot_: id 0 | task 1335 | processing task, is_child = 0 0.25.663.681 I slot print_timing: id 0 | task 1335 | prompt eval time = 152.01 ms / 430 tokens ( 0.35 ms per token, 2828.72 tokens per second) 0.25.663.687 I slot print_timing: id 0 | task 1335 | eval time = 761.24 ms / 62 tokens ( 12.48 ms per token, 80.13 tokens per second) 0.25.663.688 I slot print_timing: id 0 | task 1335 | total time = 913.25 ms / 492 tokens 0.25.663.688 I slot print_timing: id 0 | task 1335 | graphs reused = 1275 0.25.663.689 I slot print_timing: id 0 | task 1335 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.663.719 I slot release: id 0 | task 1335 | stop processing: n_tokens = 491, truncated = 0 0.25.690.912 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 25555768 0.25.726.744 I slot launch_slot_: id 0 | task 1400 | processing task, is_child = 0 0.26.636.392 I slot print_timing: id 0 | task 1400 | prompt eval time = 150.65 ms / 392 tokens ( 0.38 ms per token, 2602.01 tokens per second) 0.26.636.398 I slot print_timing: id 0 | task 1400 | eval time = 758.97 ms / 62 tokens ( 12.44 ms per token, 80.37 tokens per second) 0.26.636.399 I slot print_timing: id 0 | task 1400 | total time = 909.63 ms / 454 tokens 0.26.636.400 I slot print_timing: id 0 | task 1400 | graphs reused = 1335 0.26.636.401 I slot print_timing: id 0 | task 1400 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.636.429 I slot release: id 0 | task 1400 | stop processing: n_tokens = 453, truncated = 0 0.26.651.970 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 26528478 0.26.677.721 I slot launch_slot_: id 0 | task 1465 | processing task, is_child = 0 0.27.415.804 I slot print_timing: id 0 | task 1465 | prompt eval time = 139.44 ms / 350 tokens ( 0.40 ms per token, 2510.09 tokens per second) 0.27.415.809 I slot print_timing: id 0 | task 1465 | eval time = 598.62 ms / 49 tokens ( 12.47 ms per token, 80.18 tokens per second) 0.27.415.810 I slot print_timing: id 0 | task 1465 | total time = 738.06 ms / 399 tokens 0.27.415.811 I slot print_timing: id 0 | task 1465 | graphs reused = 1382 0.27.415.811 I slot print_timing: id 0 | task 1465 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.415.839 I slot release: id 0 | task 1465 | stop processing: n_tokens = 398, truncated = 0 0.27.432.788 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 27307887 0.27.458.115 I slot launch_slot_: id 0 | task 1517 | processing task, is_child = 0 0.28.354.535 I slot print_timing: id 0 | task 1517 | prompt eval time = 148.83 ms / 380 tokens ( 0.39 ms per token, 2553.28 tokens per second) 0.28.354.540 I slot print_timing: id 0 | task 1517 | eval time = 747.57 ms / 61 tokens ( 12.46 ms per token, 80.26 tokens per second) 0.28.354.541 I slot print_timing: id 0 | task 1517 | total time = 896.40 ms / 441 tokens 0.28.354.542 I slot print_timing: id 0 | task 1517 | graphs reused = 1441 0.28.354.543 I slot print_timing: id 0 | task 1517 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.354.571 I slot release: id 0 | task 1517 | stop processing: n_tokens = 440, truncated = 0 0.28.380.330 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 28246620 0.28.405.913 I slot launch_slot_: id 0 | task 1581 | processing task, is_child = 0 0.29.571.581 I slot print_timing: id 0 | task 1581 | prompt eval time = 153.59 ms / 410 tokens ( 0.37 ms per token, 2669.44 tokens per second) 0.29.571.587 I slot print_timing: id 0 | task 1581 | eval time = 1012.06 ms / 80 tokens ( 12.81 ms per token, 78.06 tokens per second) 0.29.571.588 I slot print_timing: id 0 | task 1581 | total time = 1165.65 ms / 490 tokens 0.29.571.588 I slot print_timing: id 0 | task 1581 | graphs reused = 1519 0.29.571.589 I slot print_timing: id 0 | task 1581 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.571.618 I slot release: id 0 | task 1581 | stop processing: n_tokens = 489, truncated = 0 0.29.594.846 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 29463667 0.29.622.049 I slot launch_slot_: id 0 | task 1664 | processing task, is_child = 0 0.30.603.749 I slot print_timing: id 0 | task 1664 | prompt eval time = 148.20 ms / 387 tokens ( 0.38 ms per token, 2611.35 tokens per second) 0.30.603.755 I slot print_timing: id 0 | task 1664 | eval time = 833.48 ms / 68 tokens ( 12.44 ms per token, 80.39 tokens per second) 0.30.603.756 I slot print_timing: id 0 | task 1664 | total time = 981.68 ms / 455 tokens 0.30.603.757 I slot print_timing: id 0 | task 1664 | graphs reused = 1585 0.30.603.758 I slot print_timing: id 0 | task 1664 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.603.786 I slot release: id 0 | task 1664 | stop processing: n_tokens = 454, truncated = 0 0.30.622.906 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 30495835 0.30.648.856 I slot launch_slot_: id 0 | task 1735 | processing task, is_child = 0 0.31.510.285 I slot print_timing: id 0 | task 1735 | prompt eval time = 139.48 ms / 358 tokens ( 0.39 ms per token, 2566.64 tokens per second) 0.31.510.291 I slot print_timing: id 0 | task 1735 | eval time = 721.93 ms / 59 tokens ( 12.45 ms per token, 80.34 tokens per second) 0.31.510.292 I slot print_timing: id 0 | task 1735 | total time = 861.41 ms / 417 tokens 0.31.510.293 I slot print_timing: id 0 | task 1735 | graphs reused = 1642 0.31.510.293 I slot print_timing: id 0 | task 1735 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.510.321 I slot release: id 0 | task 1735 | stop processing: n_tokens = 416, truncated = 0 0.31.536.358 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 31402370 0.31.562.057 I slot launch_slot_: id 0 | task 1797 | processing task, is_child = 0 0.32.423.147 I slot print_timing: id 0 | task 1797 | prompt eval time = 140.68 ms / 359 tokens ( 0.39 ms per token, 2551.84 tokens per second) 0.32.423.152 I slot print_timing: id 0 | task 1797 | eval time = 720.39 ms / 56 tokens ( 13.10 ms per token, 76.35 tokens per second) 0.32.423.153 I slot print_timing: id 0 | task 1797 | total time = 861.07 ms / 415 tokens 0.32.423.154 I slot print_timing: id 0 | task 1797 | graphs reused = 1696 0.32.423.155 I slot print_timing: id 0 | task 1797 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.423.182 I slot release: id 0 | task 1797 | stop processing: n_tokens = 414, truncated = 0 0.32.439.190 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 32315231 0.32.464.809 I slot launch_slot_: id 0 | task 1856 | processing task, is_child = 0 0.33.361.032 I slot print_timing: id 0 | task 1856 | prompt eval time = 148.07 ms / 387 tokens ( 0.38 ms per token, 2613.70 tokens per second) 0.33.361.038 I slot print_timing: id 0 | task 1856 | eval time = 748.14 ms / 61 tokens ( 12.47 ms per token, 80.20 tokens per second) 0.33.361.039 I slot print_timing: id 0 | task 1856 | total time = 896.20 ms / 448 tokens 0.33.361.039 I slot print_timing: id 0 | task 1856 | graphs reused = 1755 0.33.361.040 I slot print_timing: id 0 | task 1856 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.361.072 I slot release: id 0 | task 1856 | stop processing: n_tokens = 447, truncated = 0 0.33.387.152 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 33253121 0.33.414.666 I slot launch_slot_: id 0 | task 1920 | processing task, is_child = 0 0.34.338.243 I slot print_timing: id 0 | task 1920 | prompt eval time = 149.31 ms / 410 tokens ( 0.36 ms per token, 2746.06 tokens per second) 0.34.338.249 I slot print_timing: id 0 | task 1920 | eval time = 774.25 ms / 61 tokens ( 12.90 ms per token, 77.49 tokens per second) 0.34.338.250 I slot print_timing: id 0 | task 1920 | total time = 923.56 ms / 471 tokens 0.34.338.251 I slot print_timing: id 0 | task 1920 | graphs reused = 1814 0.34.338.252 I slot print_timing: id 0 | task 1920 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.338.280 I slot release: id 0 | task 1920 | stop processing: n_tokens = 470, truncated = 0 0.34.342.056 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 34230329 0.34.368.365 I slot launch_slot_: id 0 | task 1984 | processing task, is_child = 0 0.35.117.150 I slot print_timing: id 0 | task 1984 | prompt eval time = 138.54 ms / 351 tokens ( 0.39 ms per token, 2533.60 tokens per second) 0.35.117.157 I slot print_timing: id 0 | task 1984 | eval time = 610.23 ms / 50 tokens ( 12.45 ms per token, 80.30 tokens per second) 0.35.117.158 I slot print_timing: id 0 | task 1984 | total time = 748.76 ms / 401 tokens 0.35.117.159 I slot print_timing: id 0 | task 1984 | graphs reused = 1862 0.35.117.160 I slot print_timing: id 0 | task 1984 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.117.188 I slot release: id 0 | task 1984 | stop processing: n_tokens = 400, truncated = 0 0.35.145.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 35009237 0.35.171.478 I slot launch_slot_: id 0 | task 2037 | processing task, is_child = 0 0.38.090.864 I slot print_timing: id 0 | task 2037 | prompt eval time = 148.07 ms / 393 tokens ( 0.38 ms per token, 2654.08 tokens per second) 0.38.090.871 I slot print_timing: id 0 | task 2037 | eval time = 2771.29 ms / 224 tokens ( 12.43 ms per token, 80.47 tokens per second) 0.38.090.872 I slot print_timing: id 0 | task 2037 | total time = 2919.37 ms / 617 tokens 0.38.090.872 I slot print_timing: id 0 | task 2037 | graphs reused = 2083 0.38.090.873 I slot print_timing: id 0 | task 2037 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.090.902 I slot release: id 0 | task 2037 | stop processing: n_tokens = 616, truncated = 0 0.38.112.690 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 37982951 0.38.149.562 I slot launch_slot_: id 0 | task 2264 | processing task, is_child = 0 0.38.678.734 I slot print_timing: id 0 | task 2264 | prompt eval time = 138.01 ms / 321 tokens ( 0.43 ms per token, 2325.97 tokens per second) 0.38.678.741 I slot print_timing: id 0 | task 2264 | eval time = 391.14 ms / 32 tokens ( 12.62 ms per token, 79.25 tokens per second) 0.38.678.742 I slot print_timing: id 0 | task 2264 | total time = 529.15 ms / 353 tokens 0.38.678.743 I slot print_timing: id 0 | task 2264 | graphs reused = 2113 0.38.678.744 I slot print_timing: id 0 | task 2264 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.678.772 I slot release: id 0 | task 2264 | stop processing: n_tokens = 352, truncated = 0 0.38.705.249 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 38570821 0.38.740.189 I slot launch_slot_: id 0 | task 2299 | processing task, is_child = 0 0.40.000.578 I slot print_timing: id 0 | task 2299 | prompt eval time = 138.85 ms / 330 tokens ( 0.42 ms per token, 2376.65 tokens per second) 0.40.000.584 I slot print_timing: id 0 | task 2299 | eval time = 1121.52 ms / 91 tokens ( 12.46 ms per token, 80.25 tokens per second) 0.40.000.585 I slot print_timing: id 0 | task 2299 | total time = 1260.37 ms / 421 tokens 0.40.000.586 I slot print_timing: id 0 | task 2299 | graphs reused = 2202 0.40.000.587 I slot print_timing: id 0 | task 2299 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.000.615 I slot release: id 0 | task 2299 | stop processing: n_tokens = 420, truncated = 0 0.40.028.833 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 39892664 0.40.065.005 I slot launch_slot_: id 0 | task 2393 | processing task, is_child = 0 0.40.599.111 I slot print_timing: id 0 | task 2393 | prompt eval time = 144.49 ms / 341 tokens ( 0.42 ms per token, 2359.99 tokens per second) 0.40.599.117 I slot print_timing: id 0 | task 2393 | eval time = 389.59 ms / 32 tokens ( 12.57 ms per token, 79.57 tokens per second) 0.40.599.118 I slot print_timing: id 0 | task 2393 | total time = 534.09 ms / 373 tokens 0.40.599.118 I slot print_timing: id 0 | task 2393 | graphs reused = 2232 0.40.599.119 I slot print_timing: id 0 | task 2393 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.599.149 I slot release: id 0 | task 2393 | stop processing: n_tokens = 372, truncated = 0 0.40.602.698 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 40491197 0.40.640.790 I slot launch_slot_: id 0 | task 2428 | processing task, is_child = 0 0.41.364.630 I slot print_timing: id 0 | task 2428 | prompt eval time = 138.01 ms / 338 tokens ( 0.41 ms per token, 2449.13 tokens per second) 0.41.364.636 I slot print_timing: id 0 | task 2428 | eval time = 585.81 ms / 48 tokens ( 12.46 ms per token, 80.23 tokens per second) 0.41.364.637 I slot print_timing: id 0 | task 2428 | total time = 723.82 ms / 386 tokens 0.41.364.638 I slot print_timing: id 0 | task 2428 | graphs reused = 2278 0.41.364.639 I slot print_timing: id 0 | task 2428 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.364.666 I slot release: id 0 | task 2428 | stop processing: n_tokens = 385, truncated = 0 0.41.385.066 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 41256715 0.41.425.565 I slot launch_slot_: id 0 | task 2479 | processing task, is_child = 0 0.42.264.436 I slot print_timing: id 0 | task 2479 | prompt eval time = 153.77 ms / 395 tokens ( 0.39 ms per token, 2568.72 tokens per second) 0.42.264.441 I slot print_timing: id 0 | task 2479 | eval time = 685.08 ms / 56 tokens ( 12.46 ms per token, 80.28 tokens per second) 0.42.264.442 I slot print_timing: id 0 | task 2479 | total time = 838.85 ms / 451 tokens 0.42.264.443 I slot print_timing: id 0 | task 2479 | graphs reused = 2332 0.42.264.444 I slot print_timing: id 0 | task 2479 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.264.472 I slot release: id 0 | task 2479 | stop processing: n_tokens = 450, truncated = 0 0.42.293.456 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 42156521 0.42.332.978 I slot launch_slot_: id 0 | task 2538 | processing task, is_child = 0 0.43.570.919 I slot print_timing: id 0 | task 2538 | prompt eval time = 215.88 ms / 528 tokens ( 0.41 ms per token, 2445.76 tokens per second) 0.43.570.925 I slot print_timing: id 0 | task 2538 | eval time = 1022.04 ms / 83 tokens ( 12.46 ms per token, 80.23 tokens per second) 0.43.570.926 I slot print_timing: id 0 | task 2538 | total time = 1237.92 ms / 611 tokens 0.43.570.926 I slot print_timing: id 0 | task 2538 | graphs reused = 2413 0.43.570.927 I slot print_timing: id 0 | task 2538 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.570.959 I slot release: id 0 | task 2538 | stop processing: n_tokens = 610, truncated = 0 0.43.587.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 43463008 0.43.639.545 I slot launch_slot_: id 0 | task 2625 | processing task, is_child = 0 0.44.349.415 I slot print_timing: id 0 | task 2625 | prompt eval time = 159.00 ms / 331 tokens ( 0.48 ms per token, 2081.70 tokens per second) 0.44.349.421 I slot print_timing: id 0 | task 2625 | eval time = 550.85 ms / 45 tokens ( 12.52 ms per token, 79.88 tokens per second) 0.44.349.422 I slot print_timing: id 0 | task 2625 | total time = 709.85 ms / 376 tokens 0.44.349.423 I slot print_timing: id 0 | task 2625 | graphs reused = 2456 0.44.349.424 I slot print_timing: id 0 | task 2625 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.349.452 I slot release: id 0 | task 2625 | stop processing: n_tokens = 387, truncated = 0 0.44.367.167 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 44241501 0.44.411.409 I slot launch_slot_: id 0 | task 2673 | processing task, is_child = 0 0.45.233.783 I slot print_timing: id 0 | task 2673 | prompt eval time = 174.52 ms / 362 tokens ( 0.48 ms per token, 2074.27 tokens per second) 0.45.233.789 I slot print_timing: id 0 | task 2673 | eval time = 647.83 ms / 53 tokens ( 12.46 ms per token, 80.27 tokens per second) 0.45.233.790 I slot print_timing: id 0 | task 2673 | total time = 822.35 ms / 415 tokens 0.45.233.791 I slot print_timing: id 0 | task 2673 | graphs reused = 2507 0.45.233.791 I slot print_timing: id 0 | task 2673 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.233.819 I slot release: id 0 | task 2673 | stop processing: n_tokens = 426, truncated = 0 0.45.252.469 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 45125868 0.45.306.790 I slot launch_slot_: id 0 | task 2729 | processing task, is_child = 0 0.46.327.137 I slot print_timing: id 0 | task 2729 | prompt eval time = 172.40 ms / 419 tokens ( 0.41 ms per token, 2430.44 tokens per second) 0.46.327.143 I slot print_timing: id 0 | task 2729 | eval time = 847.93 ms / 69 tokens ( 12.47 ms per token, 80.20 tokens per second) 0.46.327.144 I slot print_timing: id 0 | task 2729 | total time = 1020.33 ms / 488 tokens 0.46.327.145 I slot print_timing: id 0 | task 2729 | graphs reused = 2574 0.46.327.146 I slot print_timing: id 0 | task 2729 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.327.176 I slot release: id 0 | task 2729 | stop processing: n_tokens = 499, truncated = 0 0.46.346.774 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 46219225 0.46.397.562 I slot launch_slot_: id 0 | task 2801 | processing task, is_child = 0 0.47.123.118 I slot print_timing: id 0 | task 2801 | prompt eval time = 187.22 ms / 423 tokens ( 0.44 ms per token, 2259.34 tokens per second) 0.47.123.124 I slot print_timing: id 0 | task 2801 | eval time = 538.31 ms / 44 tokens ( 12.52 ms per token, 79.88 tokens per second) 0.47.123.125 I slot print_timing: id 0 | task 2801 | total time = 725.54 ms / 467 tokens 0.47.123.126 I slot print_timing: id 0 | task 2801 | graphs reused = 2616 0.47.123.127 I slot print_timing: id 0 | task 2801 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.123.159 I slot release: id 0 | task 2801 | stop processing: n_tokens = 478, truncated = 0 0.47.126.949 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 47015208 0.47.171.767 I slot launch_slot_: id 0 | task 2848 | processing task, is_child = 0 0.47.856.622 I slot print_timing: id 0 | task 2848 | prompt eval time = 158.91 ms / 341 tokens ( 0.47 ms per token, 2145.81 tokens per second) 0.47.856.628 I slot print_timing: id 0 | task 2848 | eval time = 525.92 ms / 43 tokens ( 12.52 ms per token, 79.86 tokens per second) 0.47.856.629 I slot print_timing: id 0 | task 2848 | total time = 684.84 ms / 384 tokens 0.47.856.630 I slot print_timing: id 0 | task 2848 | graphs reused = 2657 0.47.856.631 I slot print_timing: id 0 | task 2848 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.856.659 I slot release: id 0 | task 2848 | stop processing: n_tokens = 395, truncated = 0 0.47.878.184 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 47748708 0.47.923.008 I slot launch_slot_: id 0 | task 2894 | processing task, is_child = 0 0.48.659.189 I slot print_timing: id 0 | task 2894 | prompt eval time = 161.99 ms / 356 tokens ( 0.46 ms per token, 2197.67 tokens per second) 0.48.659.195 I slot print_timing: id 0 | task 2894 | eval time = 574.17 ms / 47 tokens ( 12.48 ms per token, 80.12 tokens per second) 0.48.659.196 I slot print_timing: id 0 | task 2894 | total time = 736.16 ms / 403 tokens 0.48.659.197 I slot print_timing: id 0 | task 2894 | graphs reused = 2702 0.48.659.198 I slot print_timing: id 0 | task 2894 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.659.226 I slot release: id 0 | task 2894 | stop processing: n_tokens = 414, truncated = 0 0.48.686.334 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 48551275 0.48.686.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.511 MiB) 0.48.746.304 I slot launch_slot_: id 0 | task 2944 | processing task, is_child = 0 0.49.477.344 I slot print_timing: id 0 | task 2944 | prompt eval time = 167.93 ms / 362 tokens ( 0.46 ms per token, 2155.71 tokens per second) 0.49.477.350 I slot print_timing: id 0 | task 2944 | eval time = 563.09 ms / 46 tokens ( 12.51 ms per token, 79.92 tokens per second) 0.49.477.351 I slot print_timing: id 0 | task 2944 | total time = 731.02 ms / 408 tokens 0.49.477.353 I slot print_timing: id 0 | task 2944 | graphs reused = 2746 0.49.477.354 I slot print_timing: id 0 | task 2944 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.477.382 I slot release: id 0 | task 2944 | stop processing: n_tokens = 419, truncated = 0 0.49.495.191 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 49369431 0.49.495.243 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.49.557.239 I slot launch_slot_: id 0 | task 2993 | processing task, is_child = 0 0.50.561.941 I slot print_timing: id 0 | task 2993 | prompt eval time = 169.50 ms / 391 tokens ( 0.43 ms per token, 2306.77 tokens per second) 0.50.561.947 I slot print_timing: id 0 | task 2993 | eval time = 835.18 ms / 68 tokens ( 12.47 ms per token, 80.22 tokens per second) 0.50.561.949 I slot print_timing: id 0 | task 2993 | total time = 1004.68 ms / 459 tokens 0.50.561.949 I slot print_timing: id 0 | task 2993 | graphs reused = 2812 0.50.561.950 I slot print_timing: id 0 | task 2993 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.561.980 I slot release: id 0 | task 2993 | stop processing: n_tokens = 470, truncated = 0 0.50.583.251 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 50454029 0.50.583.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.50.630.441 I slot launch_slot_: id 0 | task 3064 | processing task, is_child = 0 0.51.450.744 I slot print_timing: id 0 | task 3064 | prompt eval time = 159.87 ms / 343 tokens ( 0.47 ms per token, 2145.45 tokens per second) 0.51.450.749 I slot print_timing: id 0 | task 3064 | eval time = 660.41 ms / 54 tokens ( 12.46 ms per token, 80.25 tokens per second) 0.51.450.750 I slot print_timing: id 0 | task 3064 | total time = 820.28 ms / 397 tokens 0.51.450.752 I slot print_timing: id 0 | task 3064 | graphs reused = 2864 0.51.450.752 I slot print_timing: id 0 | task 3064 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.450.780 I slot release: id 0 | task 3064 | stop processing: n_tokens = 408, truncated = 0 0.51.474.064 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 51342829 0.51.474.113 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.51.484.167 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.51.543.368 I slot launch_slot_: id 0 | task 3121 | processing task, is_child = 0 0.52.290.070 I slot print_timing: id 0 | task 3121 | prompt eval time = 183.55 ms / 401 tokens ( 0.46 ms per token, 2184.68 tokens per second) 0.52.290.076 I slot print_timing: id 0 | task 3121 | eval time = 563.13 ms / 46 tokens ( 12.51 ms per token, 79.91 tokens per second) 0.52.290.077 I slot print_timing: id 0 | task 3121 | total time = 746.68 ms / 447 tokens 0.52.290.078 I slot print_timing: id 0 | task 3121 | graphs reused = 2908 0.52.290.079 I slot print_timing: id 0 | task 3121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.290.112 I slot release: id 0 | task 3121 | stop processing: n_tokens = 458, truncated = 0 0.52.293.991 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 52182161 0.52.294.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.52.355.494 I slot launch_slot_: id 0 | task 3170 | processing task, is_child = 0 0.53.354.196 I slot print_timing: id 0 | task 3170 | prompt eval time = 162.34 ms / 355 tokens ( 0.46 ms per token, 2186.74 tokens per second) 0.53.354.202 I slot print_timing: id 0 | task 3170 | eval time = 836.34 ms / 68 tokens ( 12.48 ms per token, 80.11 tokens per second) 0.53.354.203 I slot print_timing: id 0 | task 3170 | total time = 998.68 ms / 423 tokens 0.53.354.204 I slot print_timing: id 0 | task 3170 | graphs reused = 2974 0.53.354.205 I slot print_timing: id 0 | task 3170 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.354.232 I slot release: id 0 | task 3170 | stop processing: n_tokens = 434, truncated = 0 0.53.368.603 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 53246281 0.53.368.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.53.426.888 I slot launch_slot_: id 0 | task 3241 | processing task, is_child = 0 0.54.324.142 I slot print_timing: id 0 | task 3241 | prompt eval time = 164.81 ms / 351 tokens ( 0.47 ms per token, 2129.71 tokens per second) 0.54.324.148 I slot print_timing: id 0 | task 3241 | eval time = 732.42 ms / 57 tokens ( 13.08 ms per token, 76.46 tokens per second) 0.54.324.149 I slot print_timing: id 0 | task 3241 | total time = 897.23 ms / 408 tokens 0.54.324.150 I slot print_timing: id 0 | task 3241 | graphs reused = 3029 0.54.324.151 I slot print_timing: id 0 | task 3241 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.324.179 I slot release: id 0 | task 3241 | stop processing: n_tokens = 419, truncated = 0 0.54.350.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 54216228 0.54.350.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.54.361.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.54.423.696 I slot launch_slot_: id 0 | task 3301 | processing task, is_child = 0 0.55.770.326 I slot print_timing: id 0 | task 3301 | prompt eval time = 194.83 ms / 475 tokens ( 0.41 ms per token, 2438.00 tokens per second) 0.55.770.332 I slot print_timing: id 0 | task 3301 | eval time = 1151.78 ms / 93 tokens ( 12.52 ms per token, 79.88 tokens per second) 0.55.770.333 I slot print_timing: id 0 | task 3301 | total time = 1346.61 ms / 568 tokens 0.55.770.333 I slot print_timing: id 0 | task 3301 | graphs reused = 3119 0.55.770.334 I slot print_timing: id 0 | task 3301 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.770.367 I slot release: id 0 | task 3301 | stop processing: n_tokens = 579, truncated = 0 0.55.794.653 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 55662416 0.55.794.710 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.386 MiB) 0.55.850.034 I slot launch_slot_: id 0 | task 3397 | processing task, is_child = 0 0.57.350.063 I slot print_timing: id 0 | task 3397 | prompt eval time = 189.31 ms / 440 tokens ( 0.43 ms per token, 2324.18 tokens per second) 0.57.350.069 I slot print_timing: id 0 | task 3397 | eval time = 1310.69 ms / 106 tokens ( 12.48 ms per token, 80.11 tokens per second) 0.57.350.070 I slot print_timing: id 0 | task 3397 | total time = 1500.01 ms / 546 tokens 0.57.350.071 I slot print_timing: id 0 | task 3397 | graphs reused = 3222 0.57.350.072 I slot print_timing: id 0 | task 3397 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.350.102 I slot release: id 0 | task 3397 | stop processing: n_tokens = 557, truncated = 0 0.57.374.115 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 57242151 0.57.374.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.57.432.075 I slot launch_slot_: id 0 | task 3506 | processing task, is_child = 0 0.58.269.393 I slot print_timing: id 0 | task 3506 | prompt eval time = 161.56 ms / 345 tokens ( 0.47 ms per token, 2135.47 tokens per second) 0.58.269.399 I slot print_timing: id 0 | task 3506 | eval time = 675.74 ms / 55 tokens ( 12.51 ms per token, 79.91 tokens per second) 0.58.269.400 I slot print_timing: id 0 | task 3506 | total time = 837.30 ms / 400 tokens 0.58.269.401 I slot print_timing: id 0 | task 3506 | graphs reused = 3275 0.58.269.401 I slot print_timing: id 0 | task 3506 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.269.430 I slot release: id 0 | task 3506 | stop processing: n_tokens = 411, truncated = 0 0.58.288.622 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 58161479 0.58.288.665 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.58.298.590 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.58.360.364 I slot launch_slot_: id 0 | task 3564 | processing task, is_child = 0 0.59.212.970 I slot print_timing: id 0 | task 3564 | prompt eval time = 169.57 ms / 382 tokens ( 0.44 ms per token, 2252.81 tokens per second) 0.59.212.975 I slot print_timing: id 0 | task 3564 | eval time = 683.02 ms / 55 tokens ( 12.65 ms per token, 79.06 tokens per second) 0.59.212.977 I slot print_timing: id 0 | task 3564 | total time = 852.59 ms / 437 tokens 0.59.212.977 I slot print_timing: id 0 | task 3564 | graphs reused = 3328 0.59.212.978 I slot print_timing: id 0 | task 3564 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.213.007 I slot release: id 0 | task 3564 | stop processing: n_tokens = 448, truncated = 0 0.59.237.184 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 59105056 0.59.237.233 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.59.291.656 I slot launch_slot_: id 0 | task 3622 | processing task, is_child = 0 1.00.000.039 I slot print_timing: id 0 | task 3622 | prompt eval time = 159.62 ms / 337 tokens ( 0.47 ms per token, 2111.32 tokens per second) 1.00.000.045 I slot print_timing: id 0 | task 3622 | eval time = 548.75 ms / 45 tokens ( 12.47 ms per token, 80.18 tokens per second) 1.00.000.047 I slot print_timing: id 0 | task 3622 | total time = 708.36 ms / 382 tokens 1.00.000.047 I slot print_timing: id 0 | task 3622 | graphs reused = 3371 1.00.000.048 I slot print_timing: id 0 | task 3622 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.000.077 I slot release: id 0 | task 3622 | stop processing: n_tokens = 393, truncated = 0 1.00.014.694 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 59892126 1.00.014.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 1.00.072.761 I slot launch_slot_: id 0 | task 3670 | processing task, is_child = 0 1.01.131.530 I slot print_timing: id 0 | task 3670 | prompt eval time = 169.56 ms / 402 tokens ( 0.42 ms per token, 2370.83 tokens per second) 1.01.131.536 I slot print_timing: id 0 | task 3670 | eval time = 889.19 ms / 70 tokens ( 12.89 ms per token, 77.60 tokens per second) 1.01.131.538 I slot print_timing: id 0 | task 3670 | total time = 1058.75 ms / 472 tokens 1.01.131.539 I slot print_timing: id 0 | task 3670 | graphs reused = 3439 1.01.131.540 I slot print_timing: id 0 | task 3670 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.131.571 I slot release: id 0 | task 3670 | stop processing: n_tokens = 483, truncated = 0 1.01.157.864 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 61023620 1.01.157.915 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 1.01.167.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 1.01.228.725 I slot launch_slot_: id 0 | task 3743 | processing task, is_child = 0 1.02.140.583 I slot print_timing: id 0 | task 3743 | prompt eval time = 214.30 ms / 549 tokens ( 0.39 ms per token, 2561.83 tokens per second) 1.02.140.589 I slot print_timing: id 0 | task 3743 | eval time = 697.54 ms / 57 tokens ( 12.46 ms per token, 80.28 tokens per second) 1.02.140.590 I slot print_timing: id 0 | task 3743 | total time = 911.84 ms / 606 tokens 1.02.140.591 I slot print_timing: id 0 | task 3743 | graphs reused = 3494 1.02.140.592 I slot print_timing: id 0 | task 3743 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.140.624 I slot release: id 0 | task 3743 | stop processing: n_tokens = 617, truncated = 0 1.02.169.983 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 62032673 1.02.170.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 1.02.235.486 I slot launch_slot_: id 0 | task 3804 | processing task, is_child = 0 1.03.181.850 I slot print_timing: id 0 | task 3804 | prompt eval time = 235.54 ms / 616 tokens ( 0.38 ms per token, 2615.24 tokens per second) 1.03.181.856 I slot print_timing: id 0 | task 3804 | eval time = 710.80 ms / 58 tokens ( 12.47 ms per token, 80.19 tokens per second) 1.03.181.857 I slot print_timing: id 0 | task 3804 | total time = 946.34 ms / 674 tokens 1.03.181.858 I slot print_timing: id 0 | task 3804 | graphs reused = 3550 1.03.181.859 I slot print_timing: id 0 | task 3804 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.181.897 I slot release: id 0 | task 3804 | stop processing: n_tokens = 685, truncated = 0 1.03.211.540 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 63073946 1.03.211.605 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.886 MiB) 1.03.221.449 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 1.03.292.276 I slot launch_slot_: id 0 | task 3866 | processing task, is_child = 0 1.04.301.413 I slot print_timing: id 0 | task 3866 | prompt eval time = 247.44 ms / 665 tokens ( 0.37 ms per token, 2687.57 tokens per second) 1.04.301.419 I slot print_timing: id 0 | task 3866 | eval time = 761.68 ms / 62 tokens ( 12.49 ms per token, 80.09 tokens per second) 1.04.301.420 I slot print_timing: id 0 | task 3866 | total time = 1009.12 ms / 727 tokens 1.04.301.421 I slot print_timing: id 0 | task 3866 | graphs reused = 3610 1.04.301.422 I slot print_timing: id 0 | task 3866 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.301.459 I slot release: id 0 | task 3866 | stop processing: n_tokens = 738, truncated = 0 1.04.328.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 64193508 1.04.329.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 1.04.338.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 1.04.441.567 I slot launch_slot_: id 0 | task 3932 | processing task, is_child = 0 1.05.360.532 I slot print_timing: id 0 | task 3932 | prompt eval time = 245.90 ms / 645 tokens ( 0.38 ms per token, 2623.06 tokens per second) 1.05.360.538 I slot print_timing: id 0 | task 3932 | eval time = 673.05 ms / 55 tokens ( 12.46 ms per token, 80.23 tokens per second) 1.05.360.539 I slot print_timing: id 0 | task 3932 | total time = 918.94 ms / 700 tokens 1.05.360.539 I slot print_timing: id 0 | task 3932 | graphs reused = 3663 1.05.360.540 I slot print_timing: id 0 | task 3932 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.360.576 I slot release: id 0 | task 3932 | stop processing: n_tokens = 711, truncated = 0 1.05.384.914 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 65252625 1.05.384.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 1.05.458.064 I slot launch_slot_: id 0 | task 3991 | processing task, is_child = 0 1.06.292.275 I slot print_timing: id 0 | task 3991 | prompt eval time = 193.90 ms / 474 tokens ( 0.41 ms per token, 2444.51 tokens per second) 1.06.292.280 I slot print_timing: id 0 | task 3991 | eval time = 640.29 ms / 52 tokens ( 12.55 ms per token, 79.65 tokens per second) 1.06.292.281 I slot print_timing: id 0 | task 3991 | total time = 834.19 ms / 526 tokens 1.06.292.282 I slot print_timing: id 0 | task 3991 | graphs reused = 3712 1.06.292.283 I slot print_timing: id 0 | task 3991 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.292.314 I slot release: id 0 | task 3991 | stop processing: n_tokens = 537, truncated = 0 1.06.318.095 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 66184363 1.06.318.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 1.06.328.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.107 MiB) 1.06.388.050 I slot launch_slot_: id 0 | task 4046 | processing task, is_child = 0 1.07.130.354 I slot print_timing: id 0 | task 4046 | prompt eval time = 230.20 ms / 617 tokens ( 0.37 ms per token, 2680.28 tokens per second) 1.07.130.359 I slot print_timing: id 0 | task 4046 | eval time = 512.08 ms / 42 tokens ( 12.49 ms per token, 80.06 tokens per second) 1.07.130.360 I slot print_timing: id 0 | task 4046 | total time = 742.28 ms / 659 tokens 1.07.130.361 I slot print_timing: id 0 | task 4046 | graphs reused = 3752 1.07.130.362 I slot print_timing: id 0 | task 4046 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.130.396 I slot release: id 0 | task 4046 | stop processing: n_tokens = 670, truncated = 0 1.07.153.657 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 67022445 1.07.153.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 1.07.231.703 I slot launch_slot_: id 0 | task 4092 | processing task, is_child = 0 1.08.046.065 I slot print_timing: id 0 | task 4092 | prompt eval time = 227.42 ms / 601 tokens ( 0.38 ms per token, 2642.70 tokens per second) 1.08.046.070 I slot print_timing: id 0 | task 4092 | eval time = 586.92 ms / 48 tokens ( 12.49 ms per token, 80.08 tokens per second) 1.08.046.071 I slot print_timing: id 0 | task 4092 | total time = 814.34 ms / 649 tokens 1.08.046.072 I slot print_timing: id 0 | task 4092 | graphs reused = 3798 1.08.046.073 I slot print_timing: id 0 | task 4092 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.046.108 I slot release: id 0 | task 4092 | stop processing: n_tokens = 660, truncated = 0 1.08.071.210 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 67938157 1.08.071.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 1.08.081.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 1.08.156.922 I slot launch_slot_: id 0 | task 4144 | processing task, is_child = 0 1.08.947.297 I slot print_timing: id 0 | task 4144 | prompt eval time = 215.42 ms / 533 tokens ( 0.40 ms per token, 2474.21 tokens per second) 1.08.947.303 I slot print_timing: id 0 | task 4144 | eval time = 574.93 ms / 47 tokens ( 12.50 ms per token, 80.01 tokens per second) 1.08.947.304 I slot print_timing: id 0 | task 4144 | total time = 790.36 ms / 580 tokens 1.08.947.305 I slot print_timing: id 0 | task 4144 | graphs reused = 3843 1.08.947.306 I slot print_timing: id 0 | task 4144 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.947.341 I slot release: id 0 | task 4144 | stop processing: n_tokens = 591, truncated = 0 1.08.974.822 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 68839389 1.08.974.881 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 1.09.041.889 I slot launch_slot_: id 0 | task 4195 | processing task, is_child = 0 1.09.891.133 I slot print_timing: id 0 | task 4195 | prompt eval time = 208.26 ms / 480 tokens ( 0.43 ms per token, 2304.79 tokens per second) 1.09.891.139 I slot print_timing: id 0 | task 4195 | eval time = 640.96 ms / 52 tokens ( 12.57 ms per token, 79.57 tokens per second) 1.09.891.140 I slot print_timing: id 0 | task 4195 | total time = 849.22 ms / 532 tokens 1.09.891.140 I slot print_timing: id 0 | task 4195 | graphs reused = 3892 1.09.891.141 I slot print_timing: id 0 | task 4195 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.891.172 I slot release: id 0 | task 4195 | stop processing: n_tokens = 560, truncated = 0 1.09.905.720 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 69783221 1.09.905.775 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 1.09.915.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 1.09.987.311 I slot launch_slot_: id 0 | task 4250 | processing task, is_child = 0 1.10.717.434 I slot print_timing: id 0 | task 4250 | prompt eval time = 217.64 ms / 567 tokens ( 0.38 ms per token, 2605.21 tokens per second) 1.10.717.439 I slot print_timing: id 0 | task 4250 | eval time = 512.46 ms / 42 tokens ( 12.50 ms per token, 80.01 tokens per second) 1.10.717.440 I slot print_timing: id 0 | task 4250 | total time = 730.10 ms / 609 tokens 1.10.717.441 I slot print_timing: id 0 | task 4250 | graphs reused = 3932 1.10.717.442 I slot print_timing: id 0 | task 4250 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.717.476 I slot release: id 0 | task 4250 | stop processing: n_tokens = 637, truncated = 0 1.10.746.372 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 70609525 1.10.746.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 1.10.756.339 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 1.10.850.840 I slot launch_slot_: id 0 | task 4296 | processing task, is_child = 0 1.11.832.553 I slot print_timing: id 0 | task 4296 | prompt eval time = 207.69 ms / 506 tokens ( 0.41 ms per token, 2436.36 tokens per second) 1.11.832.558 I slot print_timing: id 0 | task 4296 | eval time = 774.01 ms / 63 tokens ( 12.48 ms per token, 80.10 tokens per second) 1.11.832.559 I slot print_timing: id 0 | task 4296 | total time = 981.69 ms / 569 tokens 1.11.832.560 I slot print_timing: id 0 | task 4296 | graphs reused = 3993 1.11.832.560 I slot print_timing: id 0 | task 4296 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.832.593 I slot release: id 0 | task 4296 | stop processing: n_tokens = 597, truncated = 0 1.11.855.695 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 71724642 1.11.855.754 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 1.11.865.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 1.11.937.799 I slot launch_slot_: id 0 | task 4362 | processing task, is_child = 0 1.12.616.575 I slot print_timing: id 0 | task 4362 | prompt eval time = 189.64 ms / 436 tokens ( 0.43 ms per token, 2299.09 tokens per second) 1.12.616.581 I slot print_timing: id 0 | task 4362 | eval time = 489.12 ms / 40 tokens ( 12.54 ms per token, 79.74 tokens per second) 1.12.616.582 I slot print_timing: id 0 | task 4362 | total time = 678.76 ms / 476 tokens 1.12.616.582 I slot print_timing: id 0 | task 4362 | graphs reused = 4031 1.12.616.583 I slot print_timing: id 0 | task 4362 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.616.613 I slot release: id 0 | task 4362 | stop processing: n_tokens = 504, truncated = 0 1.12.620.918 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 72508662 1.12.620.970 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 1.12.697.967 I slot launch_slot_: id 0 | task 4405 | processing task, is_child = 0 1.13.665.281 I slot print_timing: id 0 | task 4405 | prompt eval time = 207.70 ms / 519 tokens ( 0.40 ms per token, 2498.81 tokens per second) 1.13.665.286 I slot print_timing: id 0 | task 4405 | eval time = 759.59 ms / 62 tokens ( 12.45 ms per token, 80.31 tokens per second) 1.13.665.288 I slot print_timing: id 0 | task 4405 | total time = 967.29 ms / 581 tokens 1.13.665.288 I slot print_timing: id 0 | task 4405 | graphs reused = 4091 1.13.665.289 I slot print_timing: id 0 | task 4405 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.665.324 I slot release: id 0 | task 4405 | stop processing: n_tokens = 609, truncated = 0 1.13.669.317 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 73557373 1.13.669.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.760 MiB) 1.13.679.117 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 1.13.759.036 I slot launch_slot_: id 0 | task 4471 | processing task, is_child = 0 1.14.519.252 I slot print_timing: id 0 | task 4471 | prompt eval time = 193.47 ms / 465 tokens ( 0.42 ms per token, 2403.52 tokens per second) 1.14.519.258 I slot print_timing: id 0 | task 4471 | eval time = 566.73 ms / 46 tokens ( 12.59 ms per token, 79.40 tokens per second) 1.14.519.261 I slot print_timing: id 0 | task 4471 | total time = 760.20 ms / 511 tokens 1.14.519.262 I slot print_timing: id 0 | task 4471 | graphs reused = 4134 1.14.519.263 I slot print_timing: id 0 | task 4471 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.519.294 I slot release: id 0 | task 4471 | stop processing: n_tokens = 542, truncated = 0 1.14.541.862 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 74411343 1.14.541.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 1.14.551.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 1.14.632.182 I slot launch_slot_: id 0 | task 4520 | processing task, is_child = 0 1.15.321.471 I slot print_timing: id 0 | task 4520 | prompt eval time = 189.16 ms / 431 tokens ( 0.44 ms per token, 2278.54 tokens per second) 1.15.321.477 I slot print_timing: id 0 | task 4520 | eval time = 500.11 ms / 41 tokens ( 12.50 ms per token, 79.98 tokens per second) 1.15.321.478 I slot print_timing: id 0 | task 4520 | total time = 689.27 ms / 472 tokens 1.15.321.478 I slot print_timing: id 0 | task 4520 | graphs reused = 4173 1.15.321.479 I slot print_timing: id 0 | task 4520 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.321.511 I slot release: id 0 | task 4520 | stop processing: n_tokens = 503, truncated = 0 1.15.349.311 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 75213560 1.15.349.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 1.15.358.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 1.15.441.432 I slot launch_slot_: id 0 | task 4564 | processing task, is_child = 0 1.16.176.283 I slot print_timing: id 0 | task 4564 | prompt eval time = 190.61 ms / 457 tokens ( 0.42 ms per token, 2397.58 tokens per second) 1.16.176.289 I slot print_timing: id 0 | task 4564 | eval time = 544.22 ms / 44 tokens ( 12.66 ms per token, 79.01 tokens per second) 1.16.176.290 I slot print_timing: id 0 | task 4564 | total time = 734.83 ms / 501 tokens 1.16.176.291 I slot print_timing: id 0 | task 4564 | graphs reused = 4214 1.16.176.292 I slot print_timing: id 0 | task 4564 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.176.322 I slot release: id 0 | task 4564 | stop processing: n_tokens = 532, truncated = 0 1.16.202.434 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 76068371 1.16.202.483 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 1.16.286.361 I slot launch_slot_: id 0 | task 4611 | processing task, is_child = 0 1.16.994.716 I slot print_timing: id 0 | task 4611 | prompt eval time = 194.34 ms / 439 tokens ( 0.44 ms per token, 2258.90 tokens per second) 1.16.994.722 I slot print_timing: id 0 | task 4611 | eval time = 513.99 ms / 42 tokens ( 12.54 ms per token, 79.77 tokens per second) 1.16.994.724 I slot print_timing: id 0 | task 4611 | total time = 708.34 ms / 481 tokens 1.16.994.725 I slot print_timing: id 0 | task 4611 | graphs reused = 4254 1.16.994.725 I slot print_timing: id 0 | task 4611 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.994.756 I slot release: id 0 | task 4611 | stop processing: n_tokens = 512, truncated = 0 1.17.011.092 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 76886805 1.17.011.143 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 1.17.023.878 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 1.17.097.385 I slot launch_slot_: id 0 | task 4656 | processing task, is_child = 0 1.18.013.088 I slot print_timing: id 0 | task 4656 | prompt eval time = 225.16 ms / 606 tokens ( 0.37 ms per token, 2691.36 tokens per second) 1.18.013.094 I slot print_timing: id 0 | task 4656 | eval time = 690.52 ms / 56 tokens ( 12.55 ms per token, 79.65 tokens per second) 1.18.013.095 I slot print_timing: id 0 | task 4656 | total time = 915.68 ms / 662 tokens 1.18.013.095 I slot print_timing: id 0 | task 4656 | graphs reused = 4308 1.18.013.096 I slot print_timing: id 0 | task 4656 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.013.132 I slot release: id 0 | task 4656 | stop processing: n_tokens = 693, truncated = 0 1.18.040.011 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 77905181 1.18.040.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.951 MiB) 1.18.053.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 1.18.153.000 I slot launch_slot_: id 0 | task 4716 | processing task, is_child = 0 1.18.857.575 I slot print_timing: id 0 | task 4716 | prompt eval time = 195.99 ms / 477 tokens ( 0.41 ms per token, 2433.76 tokens per second) 1.18.857.581 I slot print_timing: id 0 | task 4716 | eval time = 508.56 ms / 41 tokens ( 12.71 ms per token, 78.65 tokens per second) 1.18.857.582 I slot print_timing: id 0 | task 4716 | total time = 704.55 ms / 518 tokens 1.18.857.584 I slot print_timing: id 0 | task 4716 | graphs reused = 4346 1.18.857.585 I slot print_timing: id 0 | task 4716 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.857.624 I slot release: id 0 | task 4716 | stop processing: n_tokens = 549, truncated = 0 1.18.881.407 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 78749673 1.18.881.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 1.18.967.285 I slot launch_slot_: id 0 | task 4760 | processing task, is_child = 0 1.19.985.935 I slot print_timing: id 0 | task 4760 | prompt eval time = 282.46 ms / 845 tokens ( 0.33 ms per token, 2991.58 tokens per second) 1.19.985.941 I slot print_timing: id 0 | task 4760 | eval time = 736.17 ms / 60 tokens ( 12.48 ms per token, 80.14 tokens per second) 1.19.985.942 I slot print_timing: id 0 | task 4760 | total time = 1018.63 ms / 905 tokens 1.19.985.943 I slot print_timing: id 0 | task 4760 | graphs reused = 4404 1.19.985.944 I slot print_timing: id 0 | task 4760 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.985.988 I slot release: id 0 | task 4760 | stop processing: n_tokens = 936, truncated = 0 1.20.002.229 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 79878037 1.20.002.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.20.015.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.20.131.197 I slot launch_slot_: id 0 | task 4824 | processing task, is_child = 0 1.20.852.966 I slot print_timing: id 0 | task 4824 | prompt eval time = 192.85 ms / 459 tokens ( 0.42 ms per token, 2380.03 tokens per second) 1.20.852.972 I slot print_timing: id 0 | task 4824 | eval time = 528.89 ms / 43 tokens ( 12.59 ms per token, 79.41 tokens per second) 1.20.852.973 I slot print_timing: id 0 | task 4824 | total time = 721.75 ms / 502 tokens 1.20.852.974 I slot print_timing: id 0 | task 4824 | graphs reused = 4444 1.20.852.975 I slot print_timing: id 0 | task 4824 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.853.005 I slot release: id 0 | task 4824 | stop processing: n_tokens = 533, truncated = 0 1.20.876.624 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 80745054 1.20.876.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 1.20.979.733 I slot launch_slot_: id 0 | task 4870 | processing task, is_child = 0 1.21.800.879 I slot print_timing: id 0 | task 4870 | prompt eval time = 245.68 ms / 670 tokens ( 0.37 ms per token, 2727.16 tokens per second) 1.21.800.884 I slot print_timing: id 0 | task 4870 | eval time = 575.45 ms / 47 tokens ( 12.51 ms per token, 79.94 tokens per second) 1.21.800.886 I slot print_timing: id 0 | task 4870 | total time = 821.12 ms / 717 tokens 1.21.800.886 I slot print_timing: id 0 | task 4870 | graphs reused = 4489 1.21.800.887 I slot print_timing: id 0 | task 4870 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.800.928 I slot release: id 0 | task 4870 | stop processing: n_tokens = 748, truncated = 0 1.21.829.903 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 81692977 1.21.829.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 1.21.843.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.21.941.110 I slot launch_slot_: id 0 | task 4921 | processing task, is_child = 0 1.23.020.267 I slot print_timing: id 0 | task 4921 | prompt eval time = 273.36 ms / 775 tokens ( 0.35 ms per token, 2835.09 tokens per second) 1.23.020.273 I slot print_timing: id 0 | task 4921 | eval time = 805.78 ms / 63 tokens ( 13.00 ms per token, 76.94 tokens per second) 1.23.020.274 I slot print_timing: id 0 | task 4921 | total time = 1079.14 ms / 838 tokens 1.23.020.275 I slot print_timing: id 0 | task 4921 | graphs reused = 4550 1.23.020.276 I slot print_timing: id 0 | task 4921 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.020.321 I slot release: id 0 | task 4921 | stop processing: n_tokens = 869, truncated = 0 1.23.044.201 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 82912370 1.23.044.260 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.23.057.247 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 1.23.158.622 I slot launch_slot_: id 0 | task 4988 | processing task, is_child = 0 1.24.253.456 I slot print_timing: id 0 | task 4988 | prompt eval time = 222.21 ms / 573 tokens ( 0.39 ms per token, 2578.61 tokens per second) 1.24.253.462 I slot print_timing: id 0 | task 4988 | eval time = 872.60 ms / 71 tokens ( 12.47 ms per token, 80.22 tokens per second) 1.24.253.463 I slot print_timing: id 0 | task 4988 | total time = 1094.82 ms / 644 tokens 1.24.253.463 I slot print_timing: id 0 | task 4988 | graphs reused = 4619 1.24.253.464 I slot print_timing: id 0 | task 4988 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.253.501 I slot release: id 0 | task 4988 | stop processing: n_tokens = 675, truncated = 0 1.24.276.921 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 84145550 1.24.276.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.422 MiB) 1.24.290.418 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 1.24.380.735 I slot launch_slot_: id 0 | task 5063 | processing task, is_child = 0 1.25.366.910 I slot print_timing: id 0 | task 5063 | prompt eval time = 197.01 ms / 461 tokens ( 0.43 ms per token, 2339.97 tokens per second) 1.25.366.916 I slot print_timing: id 0 | task 5063 | eval time = 789.14 ms / 64 tokens ( 12.53 ms per token, 79.83 tokens per second) 1.25.366.917 I slot print_timing: id 0 | task 5063 | total time = 986.15 ms / 525 tokens 1.25.366.918 I slot print_timing: id 0 | task 5063 | graphs reused = 4680 1.25.366.919 I slot print_timing: id 0 | task 5063 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.366.951 I slot release: id 0 | task 5063 | stop processing: n_tokens = 556, truncated = 0 1.25.384.421 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 85259000 1.25.384.472 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.25.460.450 I slot launch_slot_: id 0 | task 5130 | processing task, is_child = 0 1.26.243.454 I slot print_timing: id 0 | task 5130 | prompt eval time = 224.41 ms / 609 tokens ( 0.37 ms per token, 2713.77 tokens per second) 1.26.243.459 I slot print_timing: id 0 | task 5130 | eval time = 558.57 ms / 43 tokens ( 13.30 ms per token, 75.19 tokens per second) 1.26.243.460 I slot print_timing: id 0 | task 5130 | total time = 782.98 ms / 652 tokens 1.26.243.461 I slot print_timing: id 0 | task 5130 | graphs reused = 4721 1.26.243.462 I slot print_timing: id 0 | task 5130 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.243.499 I slot release: id 0 | task 5130 | stop processing: n_tokens = 683, truncated = 0 1.26.259.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 86135548 1.26.259.782 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.26.272.745 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.26.374.612 I slot launch_slot_: id 0 | task 5177 | processing task, is_child = 0 1.27.398.871 I slot print_timing: id 0 | task 5177 | prompt eval time = 275.36 ms / 791 tokens ( 0.35 ms per token, 2872.60 tokens per second) 1.27.398.877 I slot print_timing: id 0 | task 5177 | eval time = 748.88 ms / 61 tokens ( 12.48 ms per token, 80.12 tokens per second) 1.27.398.878 I slot print_timing: id 0 | task 5177 | total time = 1024.24 ms / 852 tokens 1.27.398.879 I slot print_timing: id 0 | task 5177 | graphs reused = 4780 1.27.398.880 I slot print_timing: id 0 | task 5177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.398.921 I slot release: id 0 | task 5177 | stop processing: n_tokens = 883, truncated = 0 1.27.416.424 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 87290970 1.27.416.492 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 1.27.570.661 I slot launch_slot_: id 0 | task 5242 | processing task, is_child = 0 1.28.470.588 I slot print_timing: id 0 | task 5242 | prompt eval time = 213.65 ms / 533 tokens ( 0.40 ms per token, 2494.79 tokens per second) 1.28.470.594 I slot print_timing: id 0 | task 5242 | eval time = 686.26 ms / 56 tokens ( 12.48 ms per token, 80.14 tokens per second) 1.28.470.595 I slot print_timing: id 0 | task 5242 | total time = 899.90 ms / 589 tokens 1.28.470.596 I slot print_timing: id 0 | task 5242 | graphs reused = 4834 1.28.470.597 I slot print_timing: id 0 | task 5242 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.470.635 I slot release: id 0 | task 5242 | stop processing: n_tokens = 677, truncated = 0 1.28.485.528 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 88362684 1.28.485.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 1.28.580.657 I slot launch_slot_: id 0 | task 5302 | processing task, is_child = 0 1.29.400.575 I slot print_timing: id 0 | task 5302 | prompt eval time = 226.55 ms / 566 tokens ( 0.40 ms per token, 2498.30 tokens per second) 1.29.400.581 I slot print_timing: id 0 | task 5302 | eval time = 593.34 ms / 46 tokens ( 13.19 ms per token, 75.84 tokens per second) 1.29.400.582 I slot print_timing: id 0 | task 5302 | total time = 819.90 ms / 612 tokens 1.29.400.583 I slot print_timing: id 0 | task 5302 | graphs reused = 4878 1.29.400.584 I slot print_timing: id 0 | task 5302 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.400.621 I slot release: id 0 | task 5302 | stop processing: n_tokens = 643, truncated = 0 1.29.415.946 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 89292670 1.29.415.994 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.332 MiB) 1.29.508.924 I slot launch_slot_: id 0 | task 5352 | processing task, is_child = 0 1.30.231.905 I slot print_timing: id 0 | task 5352 | prompt eval time = 192.00 ms / 443 tokens ( 0.43 ms per token, 2307.32 tokens per second) 1.30.231.911 I slot print_timing: id 0 | task 5352 | eval time = 530.96 ms / 43 tokens ( 12.64 ms per token, 79.10 tokens per second) 1.30.231.912 I slot print_timing: id 0 | task 5352 | total time = 722.96 ms / 486 tokens 1.30.231.913 I slot print_timing: id 0 | task 5352 | graphs reused = 4918 1.30.231.913 I slot print_timing: id 0 | task 5352 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.231.944 I slot release: id 0 | task 5352 | stop processing: n_tokens = 517, truncated = 0 1.30.254.671 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 90123993 1.30.254.722 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.30.337.995 I slot launch_slot_: id 0 | task 5398 | processing task, is_child = 0 1.31.328.496 I slot print_timing: id 0 | task 5398 | prompt eval time = 191.81 ms / 487 tokens ( 0.39 ms per token, 2538.97 tokens per second) 1.31.328.502 I slot print_timing: id 0 | task 5398 | eval time = 798.67 ms / 65 tokens ( 12.48 ms per token, 80.13 tokens per second) 1.31.328.503 I slot print_timing: id 0 | task 5398 | total time = 990.48 ms / 552 tokens 1.31.328.504 I slot print_timing: id 0 | task 5398 | graphs reused = 4981 1.31.328.504 I slot print_timing: id 0 | task 5398 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.328.536 I slot release: id 0 | task 5398 | stop processing: n_tokens = 583, truncated = 0 1.31.349.238 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 91220585 1.31.349.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 1.31.437.572 I slot launch_slot_: id 0 | task 5466 | processing task, is_child = 0 1.32.214.903 I slot print_timing: id 0 | task 5466 | prompt eval time = 202.63 ms / 507 tokens ( 0.40 ms per token, 2502.04 tokens per second) 1.32.214.909 I slot print_timing: id 0 | task 5466 | eval time = 574.67 ms / 47 tokens ( 12.49 ms per token, 80.05 tokens per second) 1.32.214.910 I slot print_timing: id 0 | task 5466 | total time = 777.31 ms / 554 tokens 1.32.214.911 I slot print_timing: id 0 | task 5466 | graphs reused = 5026 1.32.214.912 I slot print_timing: id 0 | task 5466 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.214.947 I slot release: id 0 | task 5466 | stop processing: n_tokens = 585, truncated = 0 1.32.219.608 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 92106996 1.32.219.664 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 1.32.236.724 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 1.32.329.035 I slot launch_slot_: id 0 | task 5516 | processing task, is_child = 0 1.33.372.579 I slot print_timing: id 0 | task 5516 | prompt eval time = 232.65 ms / 633 tokens ( 0.37 ms per token, 2720.81 tokens per second) 1.33.372.585 I slot print_timing: id 0 | task 5516 | eval time = 810.87 ms / 66 tokens ( 12.47 ms per token, 80.16 tokens per second) 1.33.372.586 I slot print_timing: id 0 | task 5516 | total time = 1043.52 ms / 699 tokens 1.33.372.587 I slot print_timing: id 0 | task 5516 | graphs reused = 5090 1.33.372.587 I slot print_timing: id 0 | task 5516 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.372.625 I slot release: id 0 | task 5516 | stop processing: n_tokens = 730, truncated = 0 1.33.397.717 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 93264674 1.33.397.779 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.33.493.232 I slot launch_slot_: id 0 | task 5586 | processing task, is_child = 0 1.34.291.208 I slot print_timing: id 0 | task 5586 | prompt eval time = 221.65 ms / 571 tokens ( 0.39 ms per token, 2576.17 tokens per second) 1.34.291.214 I slot print_timing: id 0 | task 5586 | eval time = 576.31 ms / 47 tokens ( 12.53 ms per token, 79.82 tokens per second) 1.34.291.215 I slot print_timing: id 0 | task 5586 | total time = 797.95 ms / 618 tokens 1.34.291.216 I slot print_timing: id 0 | task 5586 | graphs reused = 5135 1.34.291.217 I slot print_timing: id 0 | task 5586 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.291.254 I slot release: id 0 | task 5586 | stop processing: n_tokens = 649, truncated = 0 1.34.315.885 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 94183303 1.34.315.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.34.413.397 I slot launch_slot_: id 0 | task 5637 | processing task, is_child = 0 1.35.225.955 I slot print_timing: id 0 | task 5637 | prompt eval time = 274.50 ms / 798 tokens ( 0.34 ms per token, 2907.06 tokens per second) 1.35.225.961 I slot print_timing: id 0 | task 5637 | eval time = 538.03 ms / 44 tokens ( 12.51 ms per token, 79.92 tokens per second) 1.35.225.962 I slot print_timing: id 0 | task 5637 | total time = 812.54 ms / 842 tokens 1.35.225.964 I slot print_timing: id 0 | task 5637 | graphs reused = 5177 1.35.225.964 I slot print_timing: id 0 | task 5637 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.226.007 I slot release: id 0 | task 5637 | stop processing: n_tokens = 873, truncated = 0 1.35.254.341 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 95118056 1.35.254.404 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.35.274.630 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 1.35.378.820 I slot launch_slot_: id 0 | task 5685 | processing task, is_child = 0 1.36.138.484 I slot print_timing: id 0 | task 5685 | prompt eval time = 222.67 ms / 572 tokens ( 0.39 ms per token, 2568.79 tokens per second) 1.36.138.490 I slot print_timing: id 0 | task 5685 | eval time = 536.97 ms / 43 tokens ( 12.79 ms per token, 78.22 tokens per second) 1.36.138.491 I slot print_timing: id 0 | task 5685 | total time = 759.64 ms / 615 tokens 1.36.138.492 I slot print_timing: id 0 | task 5685 | graphs reused = 5218 1.36.138.493 I slot print_timing: id 0 | task 5685 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.138.529 I slot release: id 0 | task 5685 | stop processing: n_tokens = 646, truncated = 0 1.36.143.029 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 96030578 1.36.143.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.36.232.248 I slot launch_slot_: id 0 | task 5732 | processing task, is_child = 0 1.37.068.297 I slot print_timing: id 0 | task 5732 | prompt eval time = 232.46 ms / 613 tokens ( 0.38 ms per token, 2636.99 tokens per second) 1.37.068.304 I slot print_timing: id 0 | task 5732 | eval time = 603.57 ms / 49 tokens ( 12.57 ms per token, 79.53 tokens per second) 1.37.068.305 I slot print_timing: id 0 | task 5732 | total time = 836.03 ms / 662 tokens 1.37.068.307 I slot print_timing: id 0 | task 5732 | graphs reused = 5265 1.37.068.308 I slot print_timing: id 0 | task 5732 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.068.343 I slot release: id 0 | task 5732 | stop processing: n_tokens = 693, truncated = 0 1.37.089.734 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 96960392 1.37.089.799 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.37.190.911 I slot launch_slot_: id 0 | task 5785 | processing task, is_child = 0 1.38.351.818 I slot print_timing: id 0 | task 5785 | prompt eval time = 220.93 ms / 580 tokens ( 0.38 ms per token, 2625.24 tokens per second) 1.38.351.824 I slot print_timing: id 0 | task 5785 | eval time = 939.95 ms / 76 tokens ( 12.53 ms per token, 79.79 tokens per second) 1.38.351.825 I slot print_timing: id 0 | task 5785 | total time = 1160.88 ms / 656 tokens 1.38.351.826 I slot print_timing: id 0 | task 5785 | graphs reused = 5339 1.38.351.827 I slot print_timing: id 0 | task 5785 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.351.865 I slot release: id 0 | task 5785 | stop processing: n_tokens = 687, truncated = 0 1.38.356.943 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 98243914 1.38.357.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.38.463.482 I slot launch_slot_: id 0 | task 5865 | processing task, is_child = 0 1.39.338.581 I slot print_timing: id 0 | task 5865 | prompt eval time = 257.31 ms / 716 tokens ( 0.36 ms per token, 2782.69 tokens per second) 1.39.338.586 I slot print_timing: id 0 | task 5865 | eval time = 617.77 ms / 50 tokens ( 12.61 ms per token, 79.32 tokens per second) 1.39.338.587 I slot print_timing: id 0 | task 5865 | total time = 875.08 ms / 766 tokens 1.39.338.588 I slot print_timing: id 0 | task 5865 | graphs reused = 5386 1.39.338.589 I slot print_timing: id 0 | task 5865 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.338.628 I slot release: id 0 | task 5865 | stop processing: n_tokens = 797, truncated = 0 1.39.359.328 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 99230677 1.39.359.389 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.39.378.535 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.39.482.666 I slot launch_slot_: id 0 | task 5919 | processing task, is_child = 0 1.41.016.666 I slot print_timing: id 0 | task 5919 | prompt eval time = 275.68 ms / 799 tokens ( 0.35 ms per token, 2898.31 tokens per second) 1.41.016.671 I slot print_timing: id 0 | task 5919 | eval time = 1258.30 ms / 102 tokens ( 12.46 ms per token, 80.27 tokens per second) 1.41.016.672 I slot print_timing: id 0 | task 5919 | total time = 1533.98 ms / 901 tokens 1.41.016.674 I slot print_timing: id 0 | task 5919 | graphs reused = 5486 1.41.016.674 I slot print_timing: id 0 | task 5919 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.016.720 I slot release: id 0 | task 5919 | stop processing: n_tokens = 932, truncated = 0 1.41.045.007 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 100908769 1.41.045.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 1.41.122.503 I slot launch_slot_: id 0 | task 6025 | processing task, is_child = 0 1.42.668.727 I slot print_timing: id 0 | task 6025 | prompt eval time = 164.86 ms / 361 tokens ( 0.46 ms per token, 2189.72 tokens per second) 1.42.668.733 I slot print_timing: id 0 | task 6025 | eval time = 1381.34 ms / 112 tokens ( 12.44 ms per token, 80.36 tokens per second) 1.42.668.734 I slot print_timing: id 0 | task 6025 | total time = 1546.20 ms / 473 tokens 1.42.668.735 I slot print_timing: id 0 | task 6025 | graphs reused = 5596 1.42.668.736 I slot print_timing: id 0 | task 6025 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.668.765 I slot release: id 0 | task 6025 | stop processing: n_tokens = 504, truncated = 0 1.42.692.874 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 102560814 1.42.692.926 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.42.781.926 I slot launch_slot_: id 0 | task 6140 | processing task, is_child = 0 1.44.294.266 I slot print_timing: id 0 | task 6140 | prompt eval time = 167.00 ms / 381 tokens ( 0.44 ms per token, 2281.38 tokens per second) 1.44.294.272 I slot print_timing: id 0 | task 6140 | eval time = 1345.31 ms / 108 tokens ( 12.57 ms per token, 79.54 tokens per second) 1.44.294.273 I slot print_timing: id 0 | task 6140 | total time = 1512.32 ms / 489 tokens 1.44.294.274 I slot print_timing: id 0 | task 6140 | graphs reused = 5701 1.44.294.275 I slot print_timing: id 0 | task 6140 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.294.308 I slot release: id 0 | task 6140 | stop processing: n_tokens = 520, truncated = 0 1.44.298.156 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 104186357 1.44.298.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.44.401.655 I slot launch_slot_: id 0 | task 6251 | processing task, is_child = 0 1.46.109.039 I slot print_timing: id 0 | task 6251 | prompt eval time = 166.53 ms / 365 tokens ( 0.46 ms per token, 2191.82 tokens per second) 1.46.109.045 I slot print_timing: id 0 | task 6251 | eval time = 1540.84 ms / 124 tokens ( 12.53 ms per token, 79.83 tokens per second) 1.46.109.046 I slot print_timing: id 0 | task 6251 | total time = 1707.36 ms / 489 tokens 1.46.109.047 I slot print_timing: id 0 | task 6251 | graphs reused = 5822 1.46.109.049 I slot print_timing: id 0 | task 6251 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.109.079 I slot release: id 0 | task 6251 | stop processing: n_tokens = 520, truncated = 0 1.46.136.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 106001128 1.46.136.832 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.46.214.376 I slot launch_slot_: id 0 | task 6378 | processing task, is_child = 0 1.47.697.005 I slot print_timing: id 0 | task 6378 | prompt eval time = 161.11 ms / 333 tokens ( 0.48 ms per token, 2066.94 tokens per second) 1.47.697.011 I slot print_timing: id 0 | task 6378 | eval time = 1321.50 ms / 107 tokens ( 12.47 ms per token, 80.21 tokens per second) 1.47.697.012 I slot print_timing: id 0 | task 6378 | total time = 1482.61 ms / 440 tokens 1.47.697.012 I slot print_timing: id 0 | task 6378 | graphs reused = 5927 1.47.697.013 I slot print_timing: id 0 | task 6378 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.697.040 I slot release: id 0 | task 6378 | stop processing: n_tokens = 471, truncated = 0 1.47.724.916 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 107589089 1.47.800.595 I slot launch_slot_: id 0 | task 6488 | processing task, is_child = 0 1.49.686.192 I slot print_timing: id 0 | task 6488 | prompt eval time = 174.64 ms / 403 tokens ( 0.43 ms per token, 2307.64 tokens per second) 1.49.686.198 I slot print_timing: id 0 | task 6488 | eval time = 1710.94 ms / 138 tokens ( 12.49 ms per token, 80.07 tokens per second) 1.49.686.199 I slot print_timing: id 0 | task 6488 | total time = 1885.58 ms / 541 tokens 1.49.686.200 I slot print_timing: id 0 | task 6488 | graphs reused = 6062 1.49.686.201 I slot print_timing: id 0 | task 6488 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.686.232 I slot release: id 0 | task 6488 | stop processing: n_tokens = 572, truncated = 0 1.49.713.415 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 109578281 1.49.713.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.49.791.498 I slot launch_slot_: id 0 | task 6629 | processing task, is_child = 0 1.52.255.733 I slot print_timing: id 0 | task 6629 | prompt eval time = 171.31 ms / 411 tokens ( 0.42 ms per token, 2399.12 tokens per second) 1.52.255.739 I slot print_timing: id 0 | task 6629 | eval time = 2292.90 ms / 185 tokens ( 12.46 ms per token, 80.25 tokens per second) 1.52.255.740 I slot print_timing: id 0 | task 6629 | total time = 2464.21 ms / 596 tokens 1.52.255.740 I slot print_timing: id 0 | task 6629 | graphs reused = 6244 1.52.255.742 I slot print_timing: id 0 | task 6629 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.255.772 I slot release: id 0 | task 6629 | stop processing: n_tokens = 627, truncated = 0 1.52.283.076 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 112147821 1.52.283.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.52.381.220 I slot launch_slot_: id 0 | task 6817 | processing task, is_child = 0 1.55.365.538 I slot print_timing: id 0 | task 6817 | prompt eval time = 202.29 ms / 490 tokens ( 0.41 ms per token, 2422.29 tokens per second) 1.55.365.544 I slot print_timing: id 0 | task 6817 | eval time = 2782.01 ms / 225 tokens ( 12.42 ms per token, 80.52 tokens per second) 1.55.365.545 I slot print_timing: id 0 | task 6817 | total time = 2984.30 ms / 715 tokens 1.55.365.546 I slot print_timing: id 0 | task 6817 | graphs reused = 6467 1.55.365.547 I slot print_timing: id 0 | task 6817 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.365.581 I slot release: id 0 | task 6817 | stop processing: n_tokens = 746, truncated = 0 1.55.387.893 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 115257629 1.55.387.955 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.55.489.553 I slot launch_slot_: id 0 | task 7045 | processing task, is_child = 0 1.57.771.121 I slot print_timing: id 0 | task 7045 | prompt eval time = 167.68 ms / 344 tokens ( 0.49 ms per token, 2051.58 tokens per second) 1.57.771.127 I slot print_timing: id 0 | task 7045 | eval time = 2113.87 ms / 171 tokens ( 12.43 ms per token, 80.42 tokens per second) 1.57.771.128 I slot print_timing: id 0 | task 7045 | total time = 2281.55 ms / 515 tokens 1.57.771.129 I slot print_timing: id 0 | task 7045 | graphs reused = 6635 1.57.771.130 I slot print_timing: id 0 | task 7045 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.771.157 I slot release: id 0 | task 7045 | stop processing: n_tokens = 546, truncated = 0 1.57.797.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 117663206 1.57.797.639 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 1.57.891.350 I slot launch_slot_: id 0 | task 7219 | processing task, is_child = 0 2.00.179.594 I slot print_timing: id 0 | task 7219 | prompt eval time = 172.98 ms / 347 tokens ( 0.50 ms per token, 2006.04 tokens per second) 2.00.179.599 I slot print_timing: id 0 | task 7219 | eval time = 2115.25 ms / 171 tokens ( 12.44 ms per token, 80.37 tokens per second) 2.00.179.600 I slot print_timing: id 0 | task 7219 | total time = 2288.22 ms / 518 tokens 2.00.179.601 I slot print_timing: id 0 | task 7219 | graphs reused = 6803 2.00.179.602 I slot print_timing: id 0 | task 7219 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.179.634 I slot release: id 0 | task 7219 | stop processing: n_tokens = 549, truncated = 0 2.00.183.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 120071683 2.00.183.491 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.114 MiB) 2.00.282.868 I slot launch_slot_: id 0 | task 7393 | processing task, is_child = 0 2.02.016.412 I slot print_timing: id 0 | task 7393 | prompt eval time = 173.26 ms / 401 tokens ( 0.43 ms per token, 2314.45 tokens per second) 2.02.016.418 I slot print_timing: id 0 | task 7393 | eval time = 1560.27 ms / 126 tokens ( 12.48 ms per token, 80.11 tokens per second) 2.02.016.420 I slot print_timing: id 0 | task 7393 | total time = 1733.52 ms / 527 tokens 2.02.016.420 I slot print_timing: id 0 | task 7393 | graphs reused = 6926 2.02.016.421 I slot print_timing: id 0 | task 7393 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.016.450 I slot release: id 0 | task 7393 | stop processing: n_tokens = 558, truncated = 0 2.02.037.240 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 121908499 2.02.037.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 2.02.138.849 I slot launch_slot_: id 0 | task 7522 | processing task, is_child = 0 2.03.772.944 I slot print_timing: id 0 | task 7522 | prompt eval time = 185.00 ms / 456 tokens ( 0.41 ms per token, 2464.85 tokens per second) 2.03.772.950 I slot print_timing: id 0 | task 7522 | eval time = 1449.07 ms / 115 tokens ( 12.71 ms per token, 78.67 tokens per second) 2.03.772.950 I slot print_timing: id 0 | task 7522 | total time = 1634.07 ms / 571 tokens 2.03.772.951 I slot print_timing: id 0 | task 7522 | graphs reused = 7038 2.03.772.952 I slot print_timing: id 0 | task 7522 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.772.984 I slot release: id 0 | task 7522 | stop processing: n_tokens = 602, truncated = 0 2.03.794.972 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.078 2.03.795.026 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 2.03.893.774 I slot launch_slot_: id 0 | task 7640 | processing task, is_child = 0 2.05.459.323 I slot print_timing: id 0 | task 7640 | prompt eval time = 177.14 ms / 406 tokens ( 0.44 ms per token, 2291.99 tokens per second) 2.05.459.329 I slot print_timing: id 0 | task 7640 | eval time = 1388.39 ms / 112 tokens ( 12.51 ms per token, 79.95 tokens per second) 2.05.459.330 I slot print_timing: id 0 | task 7640 | total time = 1565.53 ms / 518 tokens 2.05.459.331 I slot print_timing: id 0 | task 7640 | graphs reused = 7147 2.05.459.331 I slot print_timing: id 0 | task 7640 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.459.361 I slot release: id 0 | task 7640 | stop processing: n_tokens = 549, truncated = 0 2.05.487.481 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 125351410 2.05.553.292 I slot launch_slot_: id 0 | task 7755 | processing task, is_child = 0 2.07.947.340 I slot print_timing: id 0 | task 7755 | prompt eval time = 175.60 ms / 406 tokens ( 0.43 ms per token, 2312.03 tokens per second) 2.07.947.346 I slot print_timing: id 0 | task 7755 | eval time = 2218.43 ms / 179 tokens ( 12.46 ms per token, 80.24 tokens per second) 2.07.947.347 I slot print_timing: id 0 | task 7755 | total time = 2394.03 ms / 585 tokens 2.07.947.348 I slot print_timing: id 0 | task 7755 | graphs reused = 7323 2.07.947.349 I slot print_timing: id 0 | task 7755 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.947.378 I slot release: id 0 | task 7755 | stop processing: n_tokens = 616, truncated = 0 2.07.970.128 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 127839427 2.07.970.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 2.08.080.400 I slot launch_slot_: id 0 | task 7937 | processing task, is_child = 0 2.10.043.759 I slot print_timing: id 0 | task 7937 | prompt eval time = 183.04 ms / 444 tokens ( 0.41 ms per token, 2425.65 tokens per second) 2.10.043.766 I slot print_timing: id 0 | task 7937 | eval time = 1780.30 ms / 144 tokens ( 12.45 ms per token, 80.32 tokens per second) 2.10.043.767 I slot print_timing: id 0 | task 7937 | total time = 1963.34 ms / 588 tokens 2.10.043.769 I slot print_timing: id 0 | task 7937 | graphs reused = 7464 2.10.043.769 I slot print_timing: id 0 | task 7937 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.043.800 I slot release: id 0 | task 7937 | stop processing: n_tokens = 619, truncated = 0 2.10.070.756 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 129935849 2.10.070.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 2.10.165.491 I slot launch_slot_: id 0 | task 8084 | processing task, is_child = 0 2.11.607.462 I slot print_timing: id 0 | task 8084 | prompt eval time = 173.96 ms / 372 tokens ( 0.47 ms per token, 2138.45 tokens per second) 2.11.607.468 I slot print_timing: id 0 | task 8084 | eval time = 1267.99 ms / 103 tokens ( 12.43 ms per token, 80.44 tokens per second) 2.11.607.469 I slot print_timing: id 0 | task 8084 | total time = 1441.95 ms / 475 tokens 2.11.607.470 I slot print_timing: id 0 | task 8084 | graphs reused = 7565 2.11.607.471 I slot print_timing: id 0 | task 8084 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.607.502 I slot release: id 0 | task 8084 | stop processing: n_tokens = 506, truncated = 0 2.11.627.056 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 131499551 2.11.627.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 2.11.721.012 I slot launch_slot_: id 0 | task 8190 | processing task, is_child = 0 2.14.757.084 I slot print_timing: id 0 | task 8190 | prompt eval time = 182.25 ms / 454 tokens ( 0.40 ms per token, 2491.03 tokens per second) 2.14.757.090 I slot print_timing: id 0 | task 8190 | eval time = 2853.80 ms / 230 tokens ( 12.46 ms per token, 80.24 tokens per second) 2.14.757.091 I slot print_timing: id 0 | task 8190 | total time = 3036.05 ms / 684 tokens 2.14.757.092 I slot print_timing: id 0 | task 8190 | graphs reused = 7792 2.14.757.093 I slot print_timing: id 0 | task 8190 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.757.127 I slot release: id 0 | task 8190 | stop processing: n_tokens = 715, truncated = 0 2.14.772.562 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 134649176 2.14.772.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 2.14.869.848 I slot launch_slot_: id 0 | task 8423 | processing task, is_child = 0 2.17.835.322 I slot print_timing: id 0 | task 8423 | prompt eval time = 168.65 ms / 354 tokens ( 0.48 ms per token, 2099.07 tokens per second) 2.17.835.328 I slot print_timing: id 0 | task 8423 | eval time = 2796.81 ms / 226 tokens ( 12.43 ms per token, 80.45 tokens per second) 2.17.835.329 I slot print_timing: id 0 | task 8423 | total time = 2965.45 ms / 580 tokens 2.17.835.330 I slot print_timing: id 0 | task 8423 | graphs reused = 8015 2.17.835.331 I slot print_timing: id 0 | task 8423 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.835.360 I slot release: id 0 | task 8423 | stop processing: n_tokens = 611, truncated = 0 2.17.864.579 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 137727409 2.17.864.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 2.17.976.552 I slot launch_slot_: id 0 | task 8652 | processing task, is_child = 0 2.19.866.677 I slot print_timing: id 0 | task 8652 | prompt eval time = 164.00 ms / 334 tokens ( 0.49 ms per token, 2036.55 tokens per second) 2.19.866.683 I slot print_timing: id 0 | task 8652 | eval time = 1726.10 ms / 140 tokens ( 12.42 ms per token, 80.53 tokens per second) 2.19.866.684 I slot print_timing: id 0 | task 8652 | total time = 1890.11 ms / 474 tokens 2.19.866.685 I slot print_timing: id 0 | task 8652 | graphs reused = 8153 2.19.866.685 I slot print_timing: id 0 | task 8652 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.866.713 I slot release: id 0 | task 8652 | stop processing: n_tokens = 505, truncated = 0 2.19.870.892 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 139758762 2.19.870.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.050 MiB) 2.19.966.531 I slot launch_slot_: id 0 | task 8795 | processing task, is_child = 0 2.22.319.174 I slot print_timing: id 0 | task 8795 | prompt eval time = 179.41 ms / 426 tokens ( 0.42 ms per token, 2374.50 tokens per second) 2.22.319.181 I slot print_timing: id 0 | task 8795 | eval time = 2173.22 ms / 175 tokens ( 12.49 ms per token, 80.07 tokens per second) 2.22.319.182 I slot print_timing: id 0 | task 8795 | total time = 2352.62 ms / 601 tokens 2.22.319.182 I slot print_timing: id 0 | task 8795 | graphs reused = 8325 2.22.319.183 I slot print_timing: id 0 | task 8795 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.319.215 I slot release: id 0 | task 8795 | stop processing: n_tokens = 632, truncated = 0 2.22.340.114 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 142211264 2.22.340.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 2.22.440.797 I slot launch_slot_: id 0 | task 8973 | processing task, is_child = 0 2.24.062.167 I slot print_timing: id 0 | task 8973 | prompt eval time = 171.11 ms / 366 tokens ( 0.47 ms per token, 2138.97 tokens per second) 2.24.062.173 I slot print_timing: id 0 | task 8973 | eval time = 1450.24 ms / 117 tokens ( 12.50 ms per token, 79.99 tokens per second) 2.24.062.174 I slot print_timing: id 0 | task 8973 | total time = 1621.35 ms / 483 tokens 2.24.062.175 I slot print_timing: id 0 | task 8973 | graphs reused = 8439 2.24.062.176 I slot print_timing: id 0 | task 8973 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.062.205 I slot release: id 0 | task 8973 | stop processing: n_tokens = 514, truncated = 0 2.24.088.673 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 143954254 2.24.088.725 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 2.24.185.678 I slot launch_slot_: id 0 | task 9093 | processing task, is_child = 0 2.27.386.770 I slot print_timing: id 0 | task 9093 | n_gen = 243, tg = 80.38 t/s, tg_3s = 80.71 t/s 2.27.634.618 I slot print_timing: id 0 | task 9093 | prompt eval time = 190.35 ms / 462 tokens ( 0.41 ms per token, 2427.11 tokens per second) 2.27.634.625 I slot print_timing: id 0 | task 9093 | eval time = 3258.57 ms / 263 tokens ( 12.44 ms per token, 80.40 tokens per second) 2.27.634.626 I slot print_timing: id 0 | task 9093 | total time = 3448.92 ms / 725 tokens 2.27.634.627 I slot print_timing: id 0 | task 9093 | graphs reused = 8699 2.27.634.628 I slot print_timing: id 0 | task 9093 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.634.667 I slot release: id 0 | task 9093 | stop processing: n_tokens = 756, truncated = 0 2.27.652.757 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 147526716 2.27.652.820 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 2.27.751.445 I slot launch_slot_: id 0 | task 9359 | processing task, is_child = 0 2.29.650.858 I slot print_timing: id 0 | task 9359 | prompt eval time = 170.93 ms / 396 tokens ( 0.43 ms per token, 2316.70 tokens per second) 2.29.650.864 I slot print_timing: id 0 | task 9359 | eval time = 1728.46 ms / 139 tokens ( 12.53 ms per token, 79.84 tokens per second) 2.29.650.865 I slot print_timing: id 0 | task 9359 | total time = 1899.39 ms / 535 tokens 2.29.650.866 I slot print_timing: id 0 | task 9359 | graphs reused = 8835 2.29.650.867 I slot print_timing: id 0 | task 9359 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.650.897 I slot release: id 0 | task 9359 | stop processing: n_tokens = 566, truncated = 0 2.29.677.652 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 149542946 2.29.744.866 I slot launch_slot_: id 0 | task 9501 | processing task, is_child = 0 2.31.922.113 I slot print_timing: id 0 | task 9501 | prompt eval time = 186.58 ms / 458 tokens ( 0.41 ms per token, 2454.71 tokens per second) 2.31.922.119 I slot print_timing: id 0 | task 9501 | eval time = 1990.65 ms / 161 tokens ( 12.44 ms per token, 80.38 tokens per second) 2.31.922.120 I slot print_timing: id 0 | task 9501 | total time = 2177.23 ms / 619 tokens 2.31.922.121 I slot print_timing: id 0 | task 9501 | graphs reused = 8993 2.31.922.122 I slot print_timing: id 0 | task 9501 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.922.153 I slot release: id 0 | task 9501 | stop processing: n_tokens = 650, truncated = 0 2.31.936.951 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 151814202 2.31.937.007 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.239 MiB) 2.32.031.938 I slot launch_slot_: id 0 | task 9665 | processing task, is_child = 0 2.34.435.528 I slot print_timing: id 0 | task 9665 | prompt eval time = 190.34 ms / 458 tokens ( 0.42 ms per token, 2406.27 tokens per second) 2.34.435.535 I slot print_timing: id 0 | task 9665 | eval time = 2213.23 ms / 176 tokens ( 12.65 ms per token, 79.07 tokens per second) 2.34.435.535 I slot print_timing: id 0 | task 9665 | total time = 2403.57 ms / 634 tokens 2.34.435.536 I slot print_timing: id 0 | task 9665 | graphs reused = 9166 2.34.435.537 I slot print_timing: id 0 | task 9665 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.435.573 I slot release: id 0 | task 9665 | stop processing: n_tokens = 665, truncated = 0 2.34.456.305 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 154327622 2.34.456.368 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 2.34.552.017 I slot launch_slot_: id 0 | task 9844 | processing task, is_child = 0 2.37.337.478 I slot print_timing: id 0 | task 9844 | prompt eval time = 186.77 ms / 452 tokens ( 0.41 ms per token, 2420.08 tokens per second) 2.37.337.483 I slot print_timing: id 0 | task 9844 | eval time = 2598.67 ms / 210 tokens ( 12.43 ms per token, 80.43 tokens per second) 2.37.337.484 I slot print_timing: id 0 | task 9844 | total time = 2785.44 ms / 662 tokens 2.37.337.485 I slot print_timing: id 0 | task 9844 | graphs reused = 9373 2.37.337.486 I slot print_timing: id 0 | task 9844 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.337.519 I slot release: id 0 | task 9844 | stop processing: n_tokens = 693, truncated = 0 2.37.366.292 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 157229567 2.37.366.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 2.37.441.207 I slot launch_slot_: id 0 | task 10057 | processing task, is_child = 0 2.39.097.998 I slot print_timing: id 0 | task 10057 | prompt eval time = 173.46 ms / 404 tokens ( 0.43 ms per token, 2329.08 tokens per second) 2.39.098.003 I slot print_timing: id 0 | task 10057 | eval time = 1483.31 ms / 120 tokens ( 12.46 ms per token, 80.23 tokens per second) 2.39.098.004 I slot print_timing: id 0 | task 10057 | total time = 1656.77 ms / 524 tokens 2.39.098.005 I slot print_timing: id 0 | task 10057 | graphs reused = 9490 2.39.098.006 I slot print_timing: id 0 | task 10057 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.098.036 I slot release: id 0 | task 10057 | stop processing: n_tokens = 555, truncated = 0 2.39.126.107 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 158990085 2.39.126.159 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 2.39.229.033 I slot launch_slot_: id 0 | task 10180 | processing task, is_child = 0 2.40.698.189 I slot print_timing: id 0 | task 10180 | prompt eval time = 164.25 ms / 345 tokens ( 0.48 ms per token, 2100.46 tokens per second) 2.40.698.195 I slot print_timing: id 0 | task 10180 | eval time = 1304.88 ms / 106 tokens ( 12.43 ms per token, 80.47 tokens per second) 2.40.698.196 I slot print_timing: id 0 | task 10180 | total time = 1469.13 ms / 451 tokens 2.40.698.197 I slot print_timing: id 0 | task 10180 | graphs reused = 9594 2.40.698.198 I slot print_timing: id 0 | task 10180 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.698.228 I slot release: id 0 | task 10180 | stop processing: n_tokens = 482, truncated = 0 2.40.713.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 160590277 2.40.713.530 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.40.790.952 I slot launch_slot_: id 0 | task 10289 | processing task, is_child = 0 2.42.277.633 I slot print_timing: id 0 | task 10289 | prompt eval time = 190.51 ms / 430 tokens ( 0.44 ms per token, 2257.15 tokens per second) 2.42.277.638 I slot print_timing: id 0 | task 10289 | eval time = 1296.15 ms / 105 tokens ( 12.46 ms per token, 80.24 tokens per second) 2.42.277.639 I slot print_timing: id 0 | task 10289 | total time = 1486.66 ms / 535 tokens 2.42.277.640 I slot print_timing: id 0 | task 10289 | graphs reused = 9696 2.42.277.640 I slot print_timing: id 0 | task 10289 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.277.669 I slot release: id 0 | task 10289 | stop processing: n_tokens = 566, truncated = 0 2.42.296.795 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 162169718 2.42.296.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.42.371.505 I slot launch_slot_: id 0 | task 10397 | processing task, is_child = 0 2.43.613.571 I slot print_timing: id 0 | task 10397 | prompt eval time = 155.67 ms / 316 tokens ( 0.49 ms per token, 2029.99 tokens per second) 2.43.613.577 I slot print_timing: id 0 | task 10397 | eval time = 1086.38 ms / 85 tokens ( 12.93 ms per token, 77.32 tokens per second) 2.43.613.578 I slot print_timing: id 0 | task 10397 | total time = 1242.05 ms / 401 tokens 2.43.613.579 I slot print_timing: id 0 | task 10397 | graphs reused = 9779 2.43.613.580 I slot print_timing: id 0 | task 10397 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.613.607 I slot release: id 0 | task 10397 | stop processing: n_tokens = 432, truncated = 0 2.43.633.338 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 163505656 2.43.633.384 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 2.43.727.962 I slot launch_slot_: id 0 | task 10485 | processing task, is_child = 0 2.45.215.181 I slot print_timing: id 0 | task 10485 | prompt eval time = 166.20 ms / 354 tokens ( 0.47 ms per token, 2129.94 tokens per second) 2.45.215.186 I slot print_timing: id 0 | task 10485 | eval time = 1321.00 ms / 107 tokens ( 12.46 ms per token, 80.24 tokens per second) 2.45.215.187 I slot print_timing: id 0 | task 10485 | total time = 1487.20 ms / 461 tokens 2.45.215.189 I slot print_timing: id 0 | task 10485 | graphs reused = 9884 2.45.215.190 I slot print_timing: id 0 | task 10485 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.215.219 I slot release: id 0 | task 10485 | stop processing: n_tokens = 492, truncated = 0 2.45.242.546 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 165107268 2.45.242.598 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 2.45.334.749 I slot launch_slot_: id 0 | task 10595 | processing task, is_child = 0 2.46.745.449 I slot print_timing: id 0 | task 10595 | prompt eval time = 190.17 ms / 438 tokens ( 0.43 ms per token, 2303.19 tokens per second) 2.46.745.455 I slot print_timing: id 0 | task 10595 | eval time = 1220.51 ms / 98 tokens ( 12.58 ms per token, 79.48 tokens per second) 2.46.745.456 I slot print_timing: id 0 | task 10595 | total time = 1410.68 ms / 536 tokens 2.46.745.456 I slot print_timing: id 0 | task 10595 | graphs reused = 9979 2.46.745.457 I slot print_timing: id 0 | task 10595 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.745.488 I slot release: id 0 | task 10595 | stop processing: n_tokens = 567, truncated = 0 2.46.765.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 166637537 2.46.766.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 2.46.863.192 I slot launch_slot_: id 0 | task 10696 | processing task, is_child = 0 2.47.926.016 I slot print_timing: id 0 | task 10696 | prompt eval time = 193.98 ms / 457 tokens ( 0.42 ms per token, 2355.91 tokens per second) 2.47.926.023 I slot print_timing: id 0 | task 10696 | eval time = 868.82 ms / 70 tokens ( 12.59 ms per token, 79.42 tokens per second) 2.47.926.024 I slot print_timing: id 0 | task 10696 | total time = 1062.80 ms / 527 tokens 2.47.926.026 I slot print_timing: id 0 | task 10696 | graphs reused = 10046 2.47.926.027 I slot print_timing: id 0 | task 10696 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.926.060 I slot release: id 0 | task 10696 | stop processing: n_tokens = 558, truncated = 0 2.47.951.989 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 167818109 2.47.952.033 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 2.48.045.223 I slot launch_slot_: id 0 | task 10769 | processing task, is_child = 0 2.49.455.552 I slot print_timing: id 0 | task 10769 | prompt eval time = 197.40 ms / 473 tokens ( 0.42 ms per token, 2396.17 tokens per second) 2.49.455.558 I slot print_timing: id 0 | task 10769 | eval time = 1212.91 ms / 98 tokens ( 12.50 ms per token, 79.97 tokens per second) 2.49.455.559 I slot print_timing: id 0 | task 10769 | total time = 1410.31 ms / 571 tokens 2.49.455.560 I slot print_timing: id 0 | task 10769 | graphs reused = 10141 2.49.455.561 I slot print_timing: id 0 | task 10769 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.455.598 I slot release: id 0 | task 10769 | stop processing: n_tokens = 602, truncated = 0 2.49.473.023 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 169347647 2.49.473.074 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.579 MiB) 2.49.565.787 I slot launch_slot_: id 0 | task 10870 | processing task, is_child = 0 2.50.089.692 I slot print_timing: id 0 | task 10870 | prompt eval time = 191.91 ms / 476 tokens ( 0.40 ms per token, 2480.39 tokens per second) 2.50.089.698 I slot print_timing: id 0 | task 10870 | eval time = 331.98 ms / 27 tokens ( 12.77 ms per token, 78.32 tokens per second) 2.50.089.700 I slot print_timing: id 0 | task 10870 | total time = 523.88 ms / 503 tokens 2.50.089.701 I slot print_timing: id 0 | task 10870 | graphs reused = 10165 2.50.089.702 I slot print_timing: id 0 | task 10870 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.089.733 I slot release: id 0 | task 10870 | stop processing: n_tokens = 534, truncated = 0 2.50.110.475 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 169981782 2.50.110.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.50.219.428 I slot launch_slot_: id 0 | task 10900 | processing task, is_child = 0 2.51.738.663 I slot print_timing: id 0 | task 10900 | prompt eval time = 197.21 ms / 466 tokens ( 0.42 ms per token, 2363.01 tokens per second) 2.51.738.669 I slot print_timing: id 0 | task 10900 | eval time = 1322.01 ms / 107 tokens ( 12.47 ms per token, 80.18 tokens per second) 2.51.738.670 I slot print_timing: id 0 | task 10900 | total time = 1519.21 ms / 573 tokens 2.51.738.671 I slot print_timing: id 0 | task 10900 | graphs reused = 10269 2.51.738.671 I slot print_timing: id 0 | task 10900 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.738.702 I slot release: id 0 | task 10900 | stop processing: n_tokens = 604, truncated = 0 2.51.766.970 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 171630751 2.51.767.026 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.51.862.130 I slot launch_slot_: id 0 | task 11010 | processing task, is_child = 0 2.52.996.942 I slot print_timing: id 0 | task 11010 | prompt eval time = 172.94 ms / 415 tokens ( 0.42 ms per token, 2399.69 tokens per second) 2.52.996.948 I slot print_timing: id 0 | task 11010 | eval time = 961.85 ms / 78 tokens ( 12.49 ms per token, 80.05 tokens per second) 2.52.996.949 I slot print_timing: id 0 | task 11010 | total time = 1134.79 ms / 493 tokens 2.52.996.950 I slot print_timing: id 0 | task 11010 | graphs reused = 10344 2.52.996.951 I slot print_timing: id 0 | task 11010 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.996.980 I slot release: id 0 | task 11010 | stop processing: n_tokens = 524, truncated = 0 2.53.010.858 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 172889029 2.53.010.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.53.104.559 I slot launch_slot_: id 0 | task 11091 | processing task, is_child = 0 2.54.053.273 I slot print_timing: id 0 | task 11091 | prompt eval time = 164.44 ms / 352 tokens ( 0.47 ms per token, 2140.65 tokens per second) 2.54.053.279 I slot print_timing: id 0 | task 11091 | eval time = 784.25 ms / 64 tokens ( 12.45 ms per token, 80.33 tokens per second) 2.54.053.281 I slot print_timing: id 0 | task 11091 | total time = 948.69 ms / 416 tokens 2.54.053.283 I slot print_timing: id 0 | task 11091 | graphs reused = 10406 2.54.053.284 I slot print_timing: id 0 | task 11091 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.053.316 I slot release: id 0 | task 11091 | stop processing: n_tokens = 447, truncated = 0 2.54.074.041 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 173945365 2.54.074.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.54.170.235 I slot launch_slot_: id 0 | task 11158 | processing task, is_child = 0 2.56.024.014 I slot print_timing: id 0 | task 11158 | prompt eval time = 216.16 ms / 550 tokens ( 0.39 ms per token, 2544.46 tokens per second) 2.56.024.019 I slot print_timing: id 0 | task 11158 | eval time = 1637.60 ms / 133 tokens ( 12.41 ms per token, 80.61 tokens per second) 2.56.024.021 I slot print_timing: id 0 | task 11158 | total time = 1853.76 ms / 683 tokens 2.56.024.022 I slot print_timing: id 0 | task 11158 | graphs reused = 10537 2.56.024.022 I slot print_timing: id 0 | task 11158 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.024.058 I slot release: id 0 | task 11158 | stop processing: n_tokens = 714, truncated = 0 2.56.039.600 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 175916107 2.56.039.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 2.56.149.512 I slot launch_slot_: id 0 | task 11295 | processing task, is_child = 0 2.59.219.455 I slot print_timing: id 0 | task 11295 | prompt eval time = 259.27 ms / 772 tokens ( 0.34 ms per token, 2977.61 tokens per second) 2.59.219.462 I slot print_timing: id 0 | task 11295 | eval time = 2810.65 ms / 226 tokens ( 12.49 ms per token, 80.05 tokens per second) 2.59.219.463 I slot print_timing: id 0 | task 11295 | total time = 3069.92 ms / 998 tokens 2.59.219.464 I slot print_timing: id 0 | task 11295 | graphs reused = 10760 2.59.219.465 I slot print_timing: id 0 | task 11295 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.219.508 I slot release: id 0 | task 11295 | stop processing: n_tokens = 1029, truncated = 0 2.59.248.736 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 179111557 2.59.248.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 2.59.361.839 I slot launch_slot_: id 0 | task 11525 | processing task, is_child = 0 3.01.901.293 I slot print_timing: id 0 | task 11525 | prompt eval time = 251.61 ms / 683 tokens ( 0.37 ms per token, 2714.55 tokens per second) 3.01.901.298 I slot print_timing: id 0 | task 11525 | eval time = 2287.82 ms / 181 tokens ( 12.71 ms per token, 78.68 tokens per second) 3.01.901.299 I slot print_timing: id 0 | task 11525 | total time = 2539.43 ms / 864 tokens 3.01.901.300 I slot print_timing: id 0 | task 11525 | graphs reused = 10938 3.01.901.301 I slot print_timing: id 0 | task 11525 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.901.339 I slot release: id 0 | task 11525 | stop processing: n_tokens = 895, truncated = 0 3.01.905.850 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 181793388 3.01.905.919 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 3.02.019.224 I slot launch_slot_: id 0 | task 11710 | processing task, is_child = 0 3.04.941.824 I slot print_timing: id 0 | task 11710 | prompt eval time = 227.21 ms / 579 tokens ( 0.39 ms per token, 2548.26 tokens per second) 3.04.941.829 I slot print_timing: id 0 | task 11710 | eval time = 2695.37 ms / 218 tokens ( 12.42 ms per token, 80.51 tokens per second) 3.04.941.830 I slot print_timing: id 0 | task 11710 | total time = 2922.58 ms / 797 tokens 3.04.941.831 I slot print_timing: id 0 | task 11710 | graphs reused = 11153 3.04.941.832 I slot print_timing: id 0 | task 11710 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.941.866 I slot release: id 0 | task 11710 | stop processing: n_tokens = 828, truncated = 0 3.04.969.184 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 184833915 3.04.969.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 3.04.988.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 3.05.089.983 I slot launch_slot_: id 0 | task 11932 | processing task, is_child = 0 3.06.603.770 I slot print_timing: id 0 | task 11932 | prompt eval time = 206.98 ms / 500 tokens ( 0.41 ms per token, 2415.73 tokens per second) 3.06.603.776 I slot print_timing: id 0 | task 11932 | eval time = 1306.79 ms / 106 tokens ( 12.45 ms per token, 80.35 tokens per second) 3.06.603.777 I slot print_timing: id 0 | task 11932 | total time = 1513.77 ms / 606 tokens 3.06.603.778 I slot print_timing: id 0 | task 11932 | graphs reused = 11257 3.06.603.779 I slot print_timing: id 0 | task 11932 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.603.811 I slot release: id 0 | task 11932 | stop processing: n_tokens = 637, truncated = 0 3.06.631.689 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 186495860 3.06.631.745 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 3.06.699.746 I slot launch_slot_: id 0 | task 12041 | processing task, is_child = 0 3.09.550.810 I slot print_timing: id 0 | task 12041 | prompt eval time = 268.21 ms / 776 tokens ( 0.35 ms per token, 2893.27 tokens per second) 3.09.550.816 I slot print_timing: id 0 | task 12041 | eval time = 2582.83 ms / 209 tokens ( 12.42 ms per token, 80.53 tokens per second) 3.09.550.817 I slot print_timing: id 0 | task 12041 | total time = 2851.04 ms / 985 tokens 3.09.550.818 I slot print_timing: id 0 | task 12041 | graphs reused = 11464 3.09.550.819 I slot print_timing: id 0 | task 12041 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.550.873 I slot release: id 0 | task 12041 | stop processing: n_tokens = 1016, truncated = 0 3.09.571.206 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 189442922 3.09.571.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 3.09.661.814 I slot launch_slot_: id 0 | task 12254 | processing task, is_child = 0 3.12.296.577 I slot print_timing: id 0 | task 12254 | prompt eval time = 201.96 ms / 504 tokens ( 0.40 ms per token, 2495.57 tokens per second) 3.12.296.583 I slot print_timing: id 0 | task 12254 | eval time = 2432.79 ms / 197 tokens ( 12.41 ms per token, 80.57 tokens per second) 3.12.296.584 I slot print_timing: id 0 | task 12254 | total time = 2634.74 ms / 701 tokens 3.12.296.585 I slot print_timing: id 0 | task 12254 | graphs reused = 11659 3.12.296.586 I slot print_timing: id 0 | task 12254 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.296.618 I slot release: id 0 | task 12254 | stop processing: n_tokens = 732, truncated = 0 3.12.315.317 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 192188667 3.12.315.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 3.12.392.149 I slot launch_slot_: id 0 | task 12454 | processing task, is_child = 0 3.15.212.183 I slot print_timing: id 0 | task 12454 | prompt eval time = 233.81 ms / 633 tokens ( 0.37 ms per token, 2707.38 tokens per second) 3.15.212.189 I slot print_timing: id 0 | task 12454 | eval time = 2586.21 ms / 207 tokens ( 12.55 ms per token, 79.65 tokens per second) 3.15.212.190 I slot print_timing: id 0 | task 12454 | total time = 2820.01 ms / 840 tokens 3.15.212.191 I slot print_timing: id 0 | task 12454 | graphs reused = 11863 3.15.212.191 I slot print_timing: id 0 | task 12454 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.212.227 I slot release: id 0 | task 12454 | stop processing: n_tokens = 871, truncated = 0 3.15.231.967 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 195104276 3.15.232.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.146 MiB) 3.15.340.532 I slot launch_slot_: id 0 | task 12665 | processing task, is_child = 0 3.17.178.961 I slot print_timing: id 0 | task 12665 | prompt eval time = 180.46 ms / 395 tokens ( 0.46 ms per token, 2188.90 tokens per second) 3.17.178.967 I slot print_timing: id 0 | task 12665 | eval time = 1657.95 ms / 134 tokens ( 12.47 ms per token, 80.22 tokens per second) 3.17.178.968 I slot print_timing: id 0 | task 12665 | total time = 1838.41 ms / 529 tokens 3.17.178.969 I slot print_timing: id 0 | task 12665 | graphs reused = 11994 3.17.178.970 I slot print_timing: id 0 | task 12665 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.179.000 I slot release: id 0 | task 12665 | stop processing: n_tokens = 560, truncated = 0 3.17.195.995 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 197071048 3.17.196.040 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 3.17.267.929 I slot launch_slot_: id 0 | task 12802 | processing task, is_child = 0 3.20.078.536 I slot print_timing: id 0 | task 12802 | prompt eval time = 222.17 ms / 584 tokens ( 0.38 ms per token, 2628.62 tokens per second) 3.20.078.542 I slot print_timing: id 0 | task 12802 | eval time = 2588.42 ms / 209 tokens ( 12.44 ms per token, 80.36 tokens per second) 3.20.078.543 I slot print_timing: id 0 | task 12802 | total time = 2810.59 ms / 793 tokens 3.20.078.544 I slot print_timing: id 0 | task 12802 | graphs reused = 12200 3.20.078.544 I slot print_timing: id 0 | task 12802 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.078.581 I slot release: id 0 | task 12802 | stop processing: n_tokens = 824, truncated = 0 3.20.106.840 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 199970630 3.20.106.902 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 3.20.211.445 I slot launch_slot_: id 0 | task 13015 | processing task, is_child = 0 3.23.313.772 I slot print_timing: id 0 | task 13015 | prompt eval time = 252.54 ms / 695 tokens ( 0.36 ms per token, 2752.07 tokens per second) 3.23.313.777 I slot print_timing: id 0 | task 13015 | eval time = 2849.77 ms / 230 tokens ( 12.44 ms per token, 80.36 tokens per second) 3.23.313.778 I slot print_timing: id 0 | task 13015 | total time = 3102.31 ms / 925 tokens 3.23.313.779 I slot print_timing: id 0 | task 13015 | graphs reused = 12427 3.23.313.780 I slot print_timing: id 0 | task 13015 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.313.818 I slot release: id 0 | task 13015 | stop processing: n_tokens = 956, truncated = 0 3.23.341.846 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 203205867 3.23.341.916 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.300 MiB) 3.23.443.296 I slot launch_slot_: id 0 | task 13249 | processing task, is_child = 0 3.26.085.091 I slot print_timing: id 0 | task 13249 | prompt eval time = 273.57 ms / 769 tokens ( 0.36 ms per token, 2811.02 tokens per second) 3.26.085.097 I slot print_timing: id 0 | task 13249 | eval time = 2368.21 ms / 191 tokens ( 12.46 ms per token, 80.23 tokens per second) 3.26.085.098 I slot print_timing: id 0 | task 13249 | total time = 2641.77 ms / 960 tokens 3.26.085.099 I slot print_timing: id 0 | task 13249 | graphs reused = 12616 3.26.085.100 I slot print_timing: id 0 | task 13249 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.085.139 I slot release: id 0 | task 13249 | stop processing: n_tokens = 991, truncated = 0 3.26.104.304 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 205977188 3.26.104.380 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 3.26.125.870 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.860 MiB) 3.26.209.733 I slot launch_slot_: id 0 | task 13444 | processing task, is_child = 0 3.27.957.489 I slot print_timing: id 0 | task 13444 | prompt eval time = 218.14 ms / 576 tokens ( 0.38 ms per token, 2640.49 tokens per second) 3.27.957.495 I slot print_timing: id 0 | task 13444 | eval time = 1529.59 ms / 124 tokens ( 12.44 ms per token, 80.41 tokens per second) 3.27.957.496 I slot print_timing: id 0 | task 13444 | total time = 1747.73 ms / 700 tokens 3.27.957.497 I slot print_timing: id 0 | task 13444 | graphs reused = 12738 3.27.957.497 I slot print_timing: id 0 | task 13444 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.957.540 I slot release: id 0 | task 13444 | stop processing: n_tokens = 731, truncated = 0 3.27.977.973 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 207849589 3.27.978.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 3.28.064.066 I slot launch_slot_: id 0 | task 13572 | processing task, is_child = 0 3.31.306.164 I slot print_timing: id 0 | task 13572 | n_gen = 242, tg = 80.33 t/s, tg_3s = 80.67 t/s 3.31.715.514 I slot print_timing: id 0 | task 13572 | prompt eval time = 242.05 ms / 655 tokens ( 0.37 ms per token, 2706.05 tokens per second) 3.31.715.519 I slot print_timing: id 0 | task 13572 | eval time = 3409.38 ms / 275 tokens ( 12.44 ms per token, 80.37 tokens per second) 3.31.715.521 I slot print_timing: id 0 | task 13572 | total time = 3651.43 ms / 930 tokens 3.31.715.521 I slot print_timing: id 0 | task 13572 | graphs reused = 13010 3.31.715.522 I slot print_timing: id 0 | task 13572 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.715.560 I slot release: id 0 | task 13572 | stop processing: n_tokens = 961, truncated = 0 3.31.734.922 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 211607609 3.31.734.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 3.31.812.477 I slot launch_slot_: id 0 | task 13851 | processing task, is_child = 0 3.33.556.195 I slot print_timing: id 0 | task 13851 | prompt eval time = 234.29 ms / 621 tokens ( 0.38 ms per token, 2650.57 tokens per second) 3.33.556.201 I slot print_timing: id 0 | task 13851 | eval time = 1509.41 ms / 121 tokens ( 12.58 ms per token, 79.50 tokens per second) 3.33.556.202 I slot print_timing: id 0 | task 13851 | total time = 1743.70 ms / 742 tokens 3.33.556.204 I slot print_timing: id 0 | task 13851 | graphs reused = 13128 3.33.556.204 I slot print_timing: id 0 | task 13851 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.556.243 I slot release: id 0 | task 13851 | stop processing: n_tokens = 773, truncated = 0 3.33.585.912 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 213448291 3.33.585.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 3.33.697.117 I slot launch_slot_: id 0 | task 13976 | processing task, is_child = 0 3.36.194.841 I slot print_timing: id 0 | task 13976 | prompt eval time = 263.19 ms / 767 tokens ( 0.34 ms per token, 2914.26 tokens per second) 3.36.194.847 I slot print_timing: id 0 | task 13976 | eval time = 2234.51 ms / 178 tokens ( 12.62 ms per token, 79.21 tokens per second) 3.36.194.848 I slot print_timing: id 0 | task 13976 | total time = 2497.70 ms / 945 tokens 3.36.194.850 I slot print_timing: id 0 | task 13976 | graphs reused = 13304 3.36.194.850 I slot print_timing: id 0 | task 13976 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.194.893 I slot release: id 0 | task 13976 | stop processing: n_tokens = 976, truncated = 0 3.36.200.112 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 216086942 3.36.200.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 3.36.309.298 I slot launch_slot_: id 0 | task 14158 | processing task, is_child = 0 3.39.156.167 I slot print_timing: id 0 | task 14158 | prompt eval time = 292.61 ms / 864 tokens ( 0.34 ms per token, 2952.71 tokens per second) 3.39.156.173 I slot print_timing: id 0 | task 14158 | eval time = 2554.23 ms / 203 tokens ( 12.64 ms per token, 79.08 tokens per second) 3.39.156.174 I slot print_timing: id 0 | task 14158 | total time = 2846.85 ms / 1067 tokens 3.39.156.175 I slot print_timing: id 0 | task 14158 | graphs reused = 13504 3.39.156.176 I slot print_timing: id 0 | task 14158 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.156.227 I slot release: id 0 | task 14158 | stop processing: n_tokens = 1098, truncated = 0 3.39.174.019 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 219048276 3.39.174.090 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 3.39.196.834 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 3.39.317.279 I slot launch_slot_: id 0 | task 14365 | processing task, is_child = 0 3.41.164.890 I slot print_timing: id 0 | task 14365 | prompt eval time = 248.07 ms / 646 tokens ( 0.38 ms per token, 2604.07 tokens per second) 3.41.164.896 I slot print_timing: id 0 | task 14365 | eval time = 1599.52 ms / 129 tokens ( 12.50 ms per token, 80.02 tokens per second) 3.41.164.897 I slot print_timing: id 0 | task 14365 | total time = 1847.59 ms / 775 tokens 3.41.164.898 I slot print_timing: id 0 | task 14365 | graphs reused = 13630 3.41.164.898 I slot print_timing: id 0 | task 14365 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.164.937 I slot release: id 0 | task 14365 | stop processing: n_tokens = 806, truncated = 0 3.41.192.346 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 221056986 3.41.192.407 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 3.41.280.433 I slot launch_slot_: id 0 | task 14498 | processing task, is_child = 0 3.44.380.077 I slot print_timing: id 0 | task 14498 | prompt eval time = 254.34 ms / 720 tokens ( 0.35 ms per token, 2830.87 tokens per second) 3.44.380.082 I slot print_timing: id 0 | task 14498 | eval time = 2845.28 ms / 222 tokens ( 12.87 ms per token, 77.67 tokens per second) 3.44.380.084 I slot print_timing: id 0 | task 14498 | total time = 3099.62 ms / 942 tokens 3.44.380.086 I slot print_timing: id 0 | task 14498 | graphs reused = 13849 3.44.380.087 I slot print_timing: id 0 | task 14498 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.380.128 I slot release: id 0 | task 14498 | stop processing: n_tokens = 973, truncated = 0 3.44.398.417 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 224272177 3.44.398.488 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.203 MiB) 3.44.505.474 I slot launch_slot_: id 0 | task 14724 | processing task, is_child = 0 3.47.370.257 I slot print_timing: id 0 | task 14724 | prompt eval time = 210.45 ms / 509 tokens ( 0.41 ms per token, 2418.60 tokens per second) 3.47.370.263 I slot print_timing: id 0 | task 14724 | eval time = 2654.31 ms / 214 tokens ( 12.46 ms per token, 80.25 tokens per second) 3.47.370.265 I slot print_timing: id 0 | task 14724 | total time = 2864.76 ms / 723 tokens 3.47.370.265 I slot print_timing: id 0 | task 14724 | graphs reused = 14061 3.47.370.266 I slot print_timing: id 0 | task 14724 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.370.300 I slot release: id 0 | task 14724 | stop processing: n_tokens = 754, truncated = 0 3.47.397.873 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 227262349 3.47.397.927 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 3.47.493.370 I slot launch_slot_: id 0 | task 14941 | processing task, is_child = 0 3.50.716.968 I slot print_timing: id 0 | task 14941 | prompt eval time = 223.35 ms / 581 tokens ( 0.38 ms per token, 2601.31 tokens per second) 3.50.716.974 I slot print_timing: id 0 | task 14941 | eval time = 3000.23 ms / 242 tokens ( 12.45 ms per token, 80.33 tokens per second) 3.50.716.975 I slot print_timing: id 0 | task 14941 | total time = 3223.58 ms / 823 tokens 3.50.716.976 I slot print_timing: id 0 | task 14941 | graphs reused = 14300 3.50.716.977 I slot print_timing: id 0 | task 14941 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.717.016 I slot release: id 0 | task 14941 | stop processing: n_tokens = 854, truncated = 0 3.50.722.324 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 230609065 3.50.722.379 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 3.50.808.250 I slot launch_slot_: id 0 | task 15187 | processing task, is_child = 0 3.53.845.583 I slot print_timing: id 0 | task 15187 | prompt eval time = 304.21 ms / 925 tokens ( 0.33 ms per token, 3040.63 tokens per second) 3.53.845.589 I slot print_timing: id 0 | task 15187 | eval time = 2733.10 ms / 220 tokens ( 12.48 ms per token, 80.13 tokens per second) 3.53.845.590 I slot print_timing: id 0 | task 15187 | total time = 3037.31 ms / 1145 tokens 3.53.845.591 I slot print_timing: id 0 | task 15187 | graphs reused = 14517 3.53.845.591 I slot print_timing: id 0 | task 15187 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.845.638 I slot release: id 0 | task 15187 | stop processing: n_tokens = 1176, truncated = 0 3.53.875.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 233737687 3.53.875.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 3.53.981.218 I slot launch_slot_: id 0 | task 15411 | processing task, is_child = 0 3.57.275.167 I slot print_timing: id 0 | task 15411 | n_gen = 239, tg = 79.21 t/s, tg_3s = 79.54 t/s 3.57.350.121 I slot print_timing: id 0 | task 15411 | prompt eval time = 289.25 ms / 885 tokens ( 0.33 ms per token, 3059.59 tokens per second) 3.57.350.126 I slot print_timing: id 0 | task 15411 | eval time = 3079.63 ms / 245 tokens ( 12.62 ms per token, 79.23 tokens per second) 3.57.350.128 I slot print_timing: id 0 | task 15411 | total time = 3368.88 ms / 1130 tokens 3.57.350.129 I slot print_timing: id 0 | task 15411 | graphs reused = 14759 3.57.350.130 I slot print_timing: id 0 | task 15411 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.350.175 I slot release: id 0 | task 15411 | stop processing: n_tokens = 1161, truncated = 0 3.57.354.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 237242224 3.57.354.637 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 3.57.466.010 I slot launch_slot_: id 0 | task 15660 | processing task, is_child = 0 3.59.146.799 I slot print_timing: id 0 | task 15660 | prompt eval time = 173.94 ms / 392 tokens ( 0.44 ms per token, 2253.70 tokens per second) 3.59.146.804 I slot print_timing: id 0 | task 15660 | eval time = 1506.83 ms / 121 tokens ( 12.56 ms per token, 79.64 tokens per second) 3.59.146.805 I slot print_timing: id 0 | task 15660 | total time = 1680.77 ms / 513 tokens 3.59.146.807 I slot print_timing: id 0 | task 15660 | graphs reused = 14877 3.59.146.808 I slot print_timing: id 0 | task 15660 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.146.838 I slot release: id 0 | task 15660 | stop processing: n_tokens = 544, truncated = 0 3.59.162.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 544, t_last = 239038887 3.59.162.906 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 3.59.260.749 I slot launch_slot_: id 0 | task 15784 | processing task, is_child = 0 4.00.999.005 I slot print_timing: id 0 | task 15784 | prompt eval time = 161.42 ms / 331 tokens ( 0.49 ms per token, 2050.50 tokens per second) 4.00.999.011 I slot print_timing: id 0 | task 15784 | eval time = 1576.81 ms / 128 tokens ( 12.42 ms per token, 80.54 tokens per second) 4.00.999.012 I slot print_timing: id 0 | task 15784 | total time = 1738.24 ms / 459 tokens 4.00.999.013 I slot print_timing: id 0 | task 15784 | graphs reused = 15003 4.00.999.013 I slot print_timing: id 0 | task 15784 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.999.041 I slot release: id 0 | task 15784 | stop processing: n_tokens = 490, truncated = 0 4.01.023.944 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 490, t_last = 240891090 4.01.023.994 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 4.01.115.492 I slot launch_slot_: id 0 | task 15915 | processing task, is_child = 0 4.03.389.396 I slot print_timing: id 0 | task 15915 | prompt eval time = 162.38 ms / 357 tokens ( 0.45 ms per token, 2198.51 tokens per second) 4.03.389.402 I slot print_timing: id 0 | task 15915 | eval time = 2111.50 ms / 171 tokens ( 12.42 ms per token, 80.51 tokens per second) 4.03.389.404 I slot print_timing: id 0 | task 15915 | total time = 2273.88 ms / 528 tokens 4.03.389.405 I slot print_timing: id 0 | task 15915 | graphs reused = 15171 4.03.389.406 I slot print_timing: id 0 | task 15915 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.389.451 I slot release: id 0 | task 15915 | stop processing: n_tokens = 559, truncated = 0 4.03.407.460 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 559, t_last = 243281500 4.03.407.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 4.03.500.563 I slot launch_slot_: id 0 | task 16089 | processing task, is_child = 0 4.04.297.239 I slot print_timing: id 0 | task 16089 | prompt eval time = 159.67 ms / 315 tokens ( 0.51 ms per token, 1972.79 tokens per second) 4.04.297.244 I slot print_timing: id 0 | task 16089 | eval time = 636.98 ms / 52 tokens ( 12.49 ms per token, 80.06 tokens per second) 4.04.297.245 I slot print_timing: id 0 | task 16089 | total time = 796.66 ms / 367 tokens 4.04.297.246 I slot print_timing: id 0 | task 16089 | graphs reused = 15221 4.04.297.247 I slot print_timing: id 0 | task 16089 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.297.276 I slot release: id 0 | task 16089 | stop processing: n_tokens = 398, truncated = 0 4.04.324.673 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 244189325 4.04.324.723 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 4.04.410.033 I slot launch_slot_: id 0 | task 16144 | processing task, is_child = 0 4.05.309.426 I slot print_timing: id 0 | task 16144 | prompt eval time = 163.96 ms / 378 tokens ( 0.43 ms per token, 2305.40 tokens per second) 4.05.309.432 I slot print_timing: id 0 | task 16144 | eval time = 735.41 ms / 60 tokens ( 12.46 ms per token, 80.23 tokens per second) 4.05.309.433 I slot print_timing: id 0 | task 16144 | total time = 899.37 ms / 438 tokens 4.05.309.434 I slot print_timing: id 0 | task 16144 | graphs reused = 15279 4.05.309.434 I slot print_timing: id 0 | task 16144 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.309.465 I slot release: id 0 | task 16144 | stop processing: n_tokens = 469, truncated = 0 4.05.323.221 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 245201514 4.05.323.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.527 MiB) 4.05.415.804 I slot launch_slot_: id 0 | task 16207 | processing task, is_child = 0 4.05.910.078 I slot print_timing: id 0 | task 16207 | prompt eval time = 154.40 ms / 295 tokens ( 0.52 ms per token, 1910.60 tokens per second) 4.05.910.084 I slot print_timing: id 0 | task 16207 | eval time = 339.85 ms / 28 tokens ( 12.59 ms per token, 79.45 tokens per second) 4.05.910.085 I slot print_timing: id 0 | task 16207 | total time = 494.25 ms / 323 tokens 4.05.910.086 I slot print_timing: id 0 | task 16207 | graphs reused = 15305 4.05.910.087 I slot print_timing: id 0 | task 16207 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.910.114 I slot release: id 0 | task 16207 | stop processing: n_tokens = 354, truncated = 0 4.05.934.446 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 245802163 4.05.934.488 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 4.06.023.582 I slot launch_slot_: id 0 | task 16238 | processing task, is_child = 0 4.08.956.281 I slot print_timing: id 0 | task 16238 | prompt eval time = 161.07 ms / 337 tokens ( 0.48 ms per token, 2092.30 tokens per second) 4.08.956.287 I slot print_timing: id 0 | task 16238 | eval time = 2771.61 ms / 224 tokens ( 12.43 ms per token, 80.46 tokens per second) 4.08.956.288 I slot print_timing: id 0 | task 16238 | total time = 2932.68 ms / 561 tokens 4.08.956.288 I slot print_timing: id 0 | task 16238 | graphs reused = 15526 4.08.956.290 I slot print_timing: id 0 | task 16238 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.956.317 I slot release: id 0 | task 16238 | stop processing: n_tokens = 592, truncated = 0 4.08.971.020 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 592, t_last = 248848366 4.08.971.064 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 4.09.067.415 I slot launch_slot_: id 0 | task 16465 | processing task, is_child = 0 4.10.182.842 I slot print_timing: id 0 | task 16465 | prompt eval time = 159.62 ms / 325 tokens ( 0.49 ms per token, 2036.12 tokens per second) 4.10.182.848 I slot print_timing: id 0 | task 16465 | eval time = 955.79 ms / 78 tokens ( 12.41 ms per token, 80.56 tokens per second) 4.10.182.850 I slot print_timing: id 0 | task 16465 | total time = 1115.41 ms / 403 tokens 4.10.182.851 I slot print_timing: id 0 | task 16465 | graphs reused = 15602 4.10.182.852 I slot print_timing: id 0 | task 16465 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.182.883 I slot release: id 0 | task 16465 | stop processing: n_tokens = 434, truncated = 0 4.10.200.882 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.074 4.10.262.206 I slot launch_slot_: id 0 | task 16546 | processing task, is_child = 0 4.11.899.430 I slot print_timing: id 0 | task 16546 | prompt eval time = 143.61 ms / 264 tokens ( 0.54 ms per token, 1838.27 tokens per second) 4.11.899.435 I slot print_timing: id 0 | task 16546 | eval time = 1493.59 ms / 121 tokens ( 12.45 ms per token, 80.34 tokens per second) 4.11.899.436 I slot print_timing: id 0 | task 16546 | total time = 1637.20 ms / 385 tokens 4.11.899.437 I slot print_timing: id 0 | task 16546 | graphs reused = 15721 4.11.899.438 I slot print_timing: id 0 | task 16546 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.899.464 I slot release: id 0 | task 16546 | stop processing: n_tokens = 416, truncated = 0 4.11.926.449 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 251791513 4.11.926.493 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 4.12.020.509 I slot launch_slot_: id 0 | task 16670 | processing task, is_child = 0 4.12.434.205 I slot print_timing: id 0 | task 16670 | prompt eval time = 161.24 ms / 331 tokens ( 0.49 ms per token, 2052.83 tokens per second) 4.12.434.211 I slot print_timing: id 0 | task 16670 | eval time = 252.44 ms / 21 tokens ( 12.62 ms per token, 79.23 tokens per second) 4.12.434.212 I slot print_timing: id 0 | task 16670 | total time = 413.68 ms / 352 tokens 4.12.434.213 I slot print_timing: id 0 | task 16670 | graphs reused = 15740 4.12.434.214 I slot print_timing: id 0 | task 16670 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.434.242 I slot release: id 0 | task 16670 | stop processing: n_tokens = 383, truncated = 0 4.12.457.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 252326291 4.12.457.277 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 4.12.550.888 I slot launch_slot_: id 0 | task 16694 | processing task, is_child = 0 4.13.372.471 I slot print_timing: id 0 | task 16694 | prompt eval time = 160.94 ms / 333 tokens ( 0.48 ms per token, 2069.11 tokens per second) 4.13.372.477 I slot print_timing: id 0 | task 16694 | eval time = 660.62 ms / 54 tokens ( 12.46 ms per token, 80.23 tokens per second) 4.13.372.479 I slot print_timing: id 0 | task 16694 | total time = 821.56 ms / 387 tokens 4.13.372.479 I slot print_timing: id 0 | task 16694 | graphs reused = 15792 4.13.372.480 I slot print_timing: id 0 | task 16694 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.372.510 I slot release: id 0 | task 16694 | stop processing: n_tokens = 418, truncated = 0 4.13.400.530 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 253264559 4.13.400.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 4.13.497.115 I slot launch_slot_: id 0 | task 16751 | processing task, is_child = 0 4.14.316.012 I slot print_timing: id 0 | task 16751 | prompt eval time = 168.71 ms / 346 tokens ( 0.49 ms per token, 2050.81 tokens per second) 4.14.316.018 I slot print_timing: id 0 | task 16751 | eval time = 650.16 ms / 53 tokens ( 12.50 ms per token, 79.98 tokens per second) 4.14.316.018 I slot print_timing: id 0 | task 16751 | total time = 818.88 ms / 399 tokens 4.14.316.020 I slot print_timing: id 0 | task 16751 | graphs reused = 15843 4.14.316.020 I slot print_timing: id 0 | task 16751 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.316.048 I slot release: id 0 | task 16751 | stop processing: n_tokens = 430, truncated = 0 4.14.343.038 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 254208097 4.14.343.084 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 4.14.419.144 I slot launch_slot_: id 0 | task 16807 | processing task, is_child = 0 4.15.237.998 I slot print_timing: id 0 | task 16807 | prompt eval time = 158.19 ms / 325 tokens ( 0.49 ms per token, 2054.53 tokens per second) 4.15.238.004 I slot print_timing: id 0 | task 16807 | eval time = 660.65 ms / 54 tokens ( 12.47 ms per token, 80.22 tokens per second) 4.15.238.005 I slot print_timing: id 0 | task 16807 | total time = 818.84 ms / 379 tokens 4.15.238.005 I slot print_timing: id 0 | task 16807 | graphs reused = 15895 4.15.238.006 I slot print_timing: id 0 | task 16807 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.238.035 I slot release: id 0 | task 16807 | stop processing: n_tokens = 410, truncated = 0 4.15.252.147 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 410, t_last = 255130084 4.15.252.191 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 4.15.336.476 I slot launch_slot_: id 0 | task 16864 | processing task, is_child = 0 4.18.037.870 I slot print_timing: id 0 | task 16864 | prompt eval time = 161.26 ms / 322 tokens ( 0.50 ms per token, 1996.82 tokens per second) 4.18.037.876 I slot print_timing: id 0 | task 16864 | eval time = 2540.12 ms / 205 tokens ( 12.45 ms per token, 80.31 tokens per second) 4.18.037.877 I slot print_timing: id 0 | task 16864 | total time = 2701.38 ms / 527 tokens 4.18.037.878 I slot print_timing: id 0 | task 16864 | graphs reused = 16097 4.18.037.878 I slot print_timing: id 0 | task 16864 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.037.905 I slot release: id 0 | task 16864 | stop processing: n_tokens = 558, truncated = 0 4.18.062.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 257929954 4.18.122.858 I slot launch_slot_: id 0 | task 17072 | processing task, is_child = 0 4.21.286.779 I slot print_timing: id 0 | task 17072 | n_gen = 243, tg = 80.59 t/s, tg_3s = 80.92 t/s 4.22.906.846 I slot print_timing: id 0 | task 17072 | prompt eval time = 160.99 ms / 338 tokens ( 0.48 ms per token, 2099.52 tokens per second) 4.22.906.852 I slot print_timing: id 0 | task 17072 | eval time = 4622.98 ms / 374 tokens ( 12.39 ms per token, 80.68 tokens per second) 4.22.906.853 I slot print_timing: id 0 | task 17072 | total time = 4783.97 ms / 712 tokens 4.22.906.853 I slot print_timing: id 0 | task 17072 | graphs reused = 16468 4.22.906.854 I slot print_timing: id 0 | task 17072 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.906.881 I slot release: id 0 | task 17072 | stop processing: n_tokens = 743, truncated = 0 4.22.925.106 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 743, t_last = 262798930 4.22.925.181 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 4.23.043.922 I slot launch_slot_: id 0 | task 17449 | processing task, is_child = 0 4.26.213.106 I slot print_timing: id 0 | task 17449 | n_gen = 242, tg = 80.13 t/s, tg_3s = 80.46 t/s 4.27.288.024 I slot print_timing: id 0 | task 17449 | prompt eval time = 161.50 ms / 347 tokens ( 0.47 ms per token, 2148.58 tokens per second) 4.27.288.029 I slot print_timing: id 0 | task 17449 | eval time = 4082.58 ms / 328 tokens ( 12.48 ms per token, 80.10 tokens per second) 4.27.288.030 I slot print_timing: id 0 | task 17449 | total time = 4244.08 ms / 675 tokens 4.27.288.031 I slot print_timing: id 0 | task 17449 | graphs reused = 16793 4.27.288.032 I slot print_timing: id 0 | task 17449 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.288.062 I slot release: id 0 | task 17449 | stop processing: n_tokens = 706, truncated = 0 4.27.307.003 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 706, t_last = 267180111 4.27.307.052 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 4.27.412.702 I slot launch_slot_: id 0 | task 17780 | processing task, is_child = 0 4.29.203.663 I slot print_timing: id 0 | task 17780 | prompt eval time = 161.78 ms / 331 tokens ( 0.49 ms per token, 2046.01 tokens per second) 4.29.203.668 I slot print_timing: id 0 | task 17780 | eval time = 1629.16 ms / 132 tokens ( 12.44 ms per token, 80.41 tokens per second) 4.29.203.669 I slot print_timing: id 0 | task 17780 | total time = 1790.94 ms / 463 tokens 4.29.203.670 I slot print_timing: id 0 | task 17780 | graphs reused = 16923 4.29.203.671 I slot print_timing: id 0 | task 17780 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.203.698 I slot release: id 0 | task 17780 | stop processing: n_tokens = 494, truncated = 0 4.29.219.695 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 269095747 4.29.219.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.277 MiB) 4.29.311.202 I slot launch_slot_: id 0 | task 17915 | processing task, is_child = 0 4.31.034.812 I slot print_timing: id 0 | task 17915 | prompt eval time = 161.28 ms / 345 tokens ( 0.47 ms per token, 2139.20 tokens per second) 4.31.034.819 I slot print_timing: id 0 | task 17915 | eval time = 1562.32 ms / 126 tokens ( 12.50 ms per token, 80.01 tokens per second) 4.31.034.820 I slot print_timing: id 0 | task 17915 | total time = 1723.59 ms / 471 tokens 4.31.034.821 I slot print_timing: id 0 | task 17915 | graphs reused = 17047 4.31.034.821 I slot print_timing: id 0 | task 17915 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.034.852 I slot release: id 0 | task 17915 | stop processing: n_tokens = 502, truncated = 0 4.31.058.595 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 502, t_last = 270926901 4.31.058.649 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 4.31.157.716 I slot launch_slot_: id 0 | task 18044 | processing task, is_child = 0 4.31.758.053 I slot print_timing: id 0 | task 18044 | prompt eval time = 162.59 ms / 320 tokens ( 0.51 ms per token, 1968.13 tokens per second) 4.31.758.059 I slot print_timing: id 0 | task 18044 | eval time = 437.73 ms / 36 tokens ( 12.51 ms per token, 79.96 tokens per second) 4.31.758.060 I slot print_timing: id 0 | task 18044 | total time = 600.32 ms / 356 tokens 4.31.758.061 I slot print_timing: id 0 | task 18044 | graphs reused = 17081 4.31.758.061 I slot print_timing: id 0 | task 18044 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.758.093 I slot release: id 0 | task 18044 | stop processing: n_tokens = 387, truncated = 0 4.31.777.229 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 271650141 4.31.777.272 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 4.31.863.913 I slot launch_slot_: id 0 | task 18083 | processing task, is_child = 0 4.32.430.315 I slot print_timing: id 0 | task 18083 | prompt eval time = 153.00 ms / 297 tokens ( 0.52 ms per token, 1941.20 tokens per second) 4.32.430.321 I slot print_timing: id 0 | task 18083 | eval time = 413.38 ms / 34 tokens ( 12.53 ms per token, 79.83 tokens per second) 4.32.430.322 I slot print_timing: id 0 | task 18083 | total time = 566.38 ms / 331 tokens 4.32.430.323 I slot print_timing: id 0 | task 18083 | graphs reused = 17113 4.32.430.323 I slot print_timing: id 0 | task 18083 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.430.350 I slot release: id 0 | task 18083 | stop processing: n_tokens = 362, truncated = 0 4.32.446.445 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 362, t_last = 272322399 4.32.446.484 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.183 MiB) 4.32.534.791 I slot launch_slot_: id 0 | task 18120 | processing task, is_child = 0 4.35.031.591 I slot print_timing: id 0 | task 18120 | prompt eval time = 161.75 ms / 343 tokens ( 0.47 ms per token, 2120.49 tokens per second) 4.35.031.597 I slot print_timing: id 0 | task 18120 | eval time = 2335.03 ms / 189 tokens ( 12.42 ms per token, 80.51 tokens per second) 4.35.031.598 I slot print_timing: id 0 | task 18120 | total time = 2496.78 ms / 532 tokens 4.35.031.599 I slot print_timing: id 0 | task 18120 | graphs reused = 17299 4.35.031.599 I slot print_timing: id 0 | task 18120 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.031.627 I slot release: id 0 | task 18120 | stop processing: n_tokens = 563, truncated = 0 4.35.055.560 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 563, t_last = 274923676 4.35.112.282 I slot launch_slot_: id 0 | task 18312 | processing task, is_child = 0 4.35.971.035 I slot print_timing: id 0 | task 18312 | prompt eval time = 171.04 ms / 371 tokens ( 0.46 ms per token, 2169.02 tokens per second) 4.35.971.041 I slot print_timing: id 0 | task 18312 | eval time = 687.69 ms / 55 tokens ( 12.73 ms per token, 78.52 tokens per second) 4.35.971.042 I slot print_timing: id 0 | task 18312 | total time = 858.73 ms / 426 tokens 4.35.971.043 I slot print_timing: id 0 | task 18312 | graphs reused = 17352 4.35.971.044 I slot print_timing: id 0 | task 18312 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.971.073 I slot release: id 0 | task 18312 | stop processing: n_tokens = 457, truncated = 0 4.35.996.009 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 275863122 4.35.996.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 4.36.093.377 I slot launch_slot_: id 0 | task 18370 | processing task, is_child = 0 4.37.834.835 I slot print_timing: id 0 | task 18370 | prompt eval time = 155.19 ms / 292 tokens ( 0.53 ms per token, 1881.61 tokens per second) 4.37.834.841 I slot print_timing: id 0 | task 18370 | eval time = 1586.25 ms / 127 tokens ( 12.59 ms per token, 79.43 tokens per second) 4.37.834.842 I slot print_timing: id 0 | task 18370 | total time = 1741.44 ms / 419 tokens 4.37.834.843 I slot print_timing: id 0 | task 18370 | graphs reused = 17477 4.37.834.844 I slot print_timing: id 0 | task 18370 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.834.871 I slot release: id 0 | task 18370 | stop processing: n_tokens = 450, truncated = 0 4.37.853.610 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 277726920 4.37.853.655 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 4.37.943.317 I slot launch_slot_: id 0 | task 18500 | processing task, is_child = 0 4.38.313.861 I slot print_timing: id 0 | task 18500 | prompt eval time = 154.72 ms / 301 tokens ( 0.51 ms per token, 1945.40 tokens per second) 4.38.313.866 I slot print_timing: id 0 | task 18500 | eval time = 215.80 ms / 18 tokens ( 12.69 ms per token, 78.78 tokens per second) 4.38.313.867 I slot print_timing: id 0 | task 18500 | total time = 370.52 ms / 319 tokens 4.38.313.868 I slot print_timing: id 0 | task 18500 | graphs reused = 17493 4.38.313.869 I slot print_timing: id 0 | task 18500 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.313.896 I slot release: id 0 | task 18500 | stop processing: n_tokens = 350, truncated = 0 4.38.332.631 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 278205945 4.38.332.667 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 4.38.425.607 I slot launch_slot_: id 0 | task 18521 | processing task, is_child = 0 4.39.341.708 I slot print_timing: id 0 | task 18521 | prompt eval time = 154.94 ms / 303 tokens ( 0.51 ms per token, 1955.62 tokens per second) 4.39.341.714 I slot print_timing: id 0 | task 18521 | eval time = 761.14 ms / 62 tokens ( 12.48 ms per token, 80.14 tokens per second) 4.39.341.715 I slot print_timing: id 0 | task 18521 | total time = 916.08 ms / 365 tokens 4.39.341.716 I slot print_timing: id 0 | task 18521 | graphs reused = 17553 4.39.341.716 I slot print_timing: id 0 | task 18521 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.341.742 I slot release: id 0 | task 18521 | stop processing: n_tokens = 396, truncated = 0 4.39.356.809 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 279233791 4.39.356.854 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 4.39.444.160 I slot launch_slot_: id 0 | task 18586 | processing task, is_child = 0 4.39.980.793 I slot print_timing: id 0 | task 18586 | prompt eval time = 160.58 ms / 321 tokens ( 0.50 ms per token, 1999.05 tokens per second) 4.39.980.799 I slot print_timing: id 0 | task 18586 | eval time = 376.04 ms / 31 tokens ( 12.53 ms per token, 79.78 tokens per second) 4.39.980.801 I slot print_timing: id 0 | task 18586 | total time = 536.62 ms / 352 tokens 4.39.980.801 I slot print_timing: id 0 | task 18586 | graphs reused = 17582 4.39.980.802 I slot print_timing: id 0 | task 18586 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.980.830 I slot release: id 0 | task 18586 | stop processing: n_tokens = 383, truncated = 0 4.39.996.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 279872879 4.39.996.782 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.516 MiB) 4.40.077.813 I slot launch_slot_: id 0 | task 18620 | processing task, is_child = 0 4.40.466.323 I slot print_timing: id 0 | task 18620 | prompt eval time = 160.71 ms / 322 tokens ( 0.50 ms per token, 2003.66 tokens per second) 4.40.466.328 I slot print_timing: id 0 | task 18620 | eval time = 227.78 ms / 19 tokens ( 12.65 ms per token, 79.02 tokens per second) 4.40.466.329 I slot print_timing: id 0 | task 18620 | total time = 388.49 ms / 341 tokens 4.40.466.330 I slot print_timing: id 0 | task 18620 | graphs reused = 17599 4.40.466.331 I slot print_timing: id 0 | task 18620 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.466.359 I slot release: id 0 | task 18620 | stop processing: n_tokens = 372, truncated = 0 4.40.493.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 280358408 4.40.493.331 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.827 MiB) 4.40.569.753 I slot launch_slot_: id 0 | task 18642 | processing task, is_child = 0 4.41.256.578 I slot print_timing: id 0 | task 18642 | prompt eval time = 160.92 ms / 323 tokens ( 0.50 ms per token, 2007.25 tokens per second) 4.41.256.584 I slot print_timing: id 0 | task 18642 | eval time = 525.88 ms / 43 tokens ( 12.52 ms per token, 79.87 tokens per second) 4.41.256.585 I slot print_timing: id 0 | task 18642 | total time = 686.80 ms / 366 tokens 4.41.256.586 I slot print_timing: id 0 | task 18642 | graphs reused = 17640 4.41.256.587 I slot print_timing: id 0 | task 18642 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.256.617 I slot release: id 0 | task 18642 | stop processing: n_tokens = 397, truncated = 0 4.41.271.112 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 281148666 4.41.271.150 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.985 MiB) 4.41.359.191 I slot launch_slot_: id 0 | task 18688 | processing task, is_child = 0 4.44.532.947 I slot print_timing: id 0 | task 18688 | n_gen = 242, tg = 80.00 t/s, tg_3s = 80.33 t/s 4.46.553.727 I slot print_timing: id 0 | task 18688 | prompt eval time = 161.33 ms / 321 tokens ( 0.50 ms per token, 1989.74 tokens per second) 4.46.553.733 I slot print_timing: id 0 | task 18688 | eval time = 5033.19 ms / 404 tokens ( 12.49 ms per token, 80.07 tokens per second) 4.46.553.734 I slot print_timing: id 0 | task 18688 | total time = 5194.52 ms / 725 tokens 4.46.553.735 I slot print_timing: id 0 | task 18688 | graphs reused = 18041 4.46.553.736 I slot print_timing: id 0 | task 18688 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.553.766 I slot release: id 0 | task 18688 | stop processing: n_tokens = 756, truncated = 0 4.46.571.622 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 286445815 4.46.571.682 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.950 MiB) 4.46.660.336 I slot launch_slot_: id 0 | task 19095 | processing task, is_child = 0 4.47.800.433 I slot print_timing: id 0 | task 19095 | prompt eval time = 160.37 ms / 322 tokens ( 0.50 ms per token, 2007.88 tokens per second) 4.47.800.439 I slot print_timing: id 0 | task 19095 | eval time = 979.71 ms / 80 tokens ( 12.40 ms per token, 80.64 tokens per second) 4.47.800.440 I slot print_timing: id 0 | task 19095 | total time = 1140.08 ms / 402 tokens 4.47.800.441 I slot print_timing: id 0 | task 19095 | graphs reused = 18119 4.47.800.442 I slot print_timing: id 0 | task 19095 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.800.471 I slot release: id 0 | task 19095 | stop processing: n_tokens = 433, truncated = 0 4.47.804.043 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 287692520 4.47.804.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.171 MiB) 4.47.889.542 I slot launch_slot_: id 0 | task 19178 | processing task, is_child = 0 4.48.614.227 I slot print_timing: id 0 | task 19178 | prompt eval time = 164.05 ms / 337 tokens ( 0.49 ms per token, 2054.30 tokens per second) 4.48.614.233 I slot print_timing: id 0 | task 19178 | eval time = 560.62 ms / 46 tokens ( 12.46 ms per token, 80.27 tokens per second) 4.48.614.234 I slot print_timing: id 0 | task 19178 | total time = 724.66 ms / 383 tokens 4.48.614.235 I slot print_timing: id 0 | task 19178 | graphs reused = 18163 4.48.614.236 I slot print_timing: id 0 | task 19178 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.614.264 I slot release: id 0 | task 19178 | stop processing: n_tokens = 414, truncated = 0 4.48.628.674 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 288506313 4.48.628.718 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 4.48.722.123 I slot launch_slot_: id 0 | task 19227 | processing task, is_child = 0 4.49.455.738 I slot print_timing: id 0 | task 19227 | prompt eval time = 160.67 ms / 325 tokens ( 0.49 ms per token, 2022.73 tokens per second) 4.49.455.744 I slot print_timing: id 0 | task 19227 | eval time = 572.92 ms / 47 tokens ( 12.45 ms per token, 80.29 tokens per second) 4.49.455.745 I slot print_timing: id 0 | task 19227 | total time = 733.59 ms / 372 tokens 4.49.455.747 I slot print_timing: id 0 | task 19227 | graphs reused = 18208 4.49.455.748 I slot print_timing: id 0 | task 19227 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.455.777 I slot release: id 0 | task 19227 | stop processing: n_tokens = 403, truncated = 0 4.49.483.618 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 289347826 4.49.483.662 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.017 MiB) 4.49.570.970 I slot launch_slot_: id 0 | task 19277 | processing task, is_child = 0 4.50.691.218 I slot print_timing: id 0 | task 19277 | prompt eval time = 161.18 ms / 331 tokens ( 0.49 ms per token, 2053.63 tokens per second) 4.50.691.224 I slot print_timing: id 0 | task 19277 | eval time = 959.05 ms / 78 tokens ( 12.46 ms per token, 80.29 tokens per second) 4.50.691.225 I slot print_timing: id 0 | task 19277 | total time = 1120.23 ms / 409 tokens 4.50.691.227 I slot print_timing: id 0 | task 19277 | graphs reused = 18284 4.50.691.228 I slot print_timing: id 0 | task 19277 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.691.258 I slot release: id 0 | task 19277 | stop processing: n_tokens = 440, truncated = 0 4.50.705.308 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 290583307 4.50.705.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.076 MiB) 4.50.784.051 I slot launch_slot_: id 0 | task 19358 | processing task, is_child = 0 4.51.519.384 I slot print_timing: id 0 | task 19358 | prompt eval time = 160.32 ms / 336 tokens ( 0.48 ms per token, 2095.86 tokens per second) 4.51.519.391 I slot print_timing: id 0 | task 19358 | eval time = 575.00 ms / 47 tokens ( 12.50 ms per token, 80.00 tokens per second) 4.51.519.392 I slot print_timing: id 0 | task 19358 | total time = 735.31 ms / 383 tokens 4.51.519.393 I slot print_timing: id 0 | task 19358 | graphs reused = 18329 4.51.519.394 I slot print_timing: id 0 | task 19358 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.519.427 I slot release: id 0 | task 19358 | stop processing: n_tokens = 414, truncated = 0 4.51.545.360 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 291411476 4.51.545.404 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.513 MiB) 4.51.615.204 I slot launch_slot_: id 0 | task 19408 | processing task, is_child = 0 4.52.153.549 I slot print_timing: id 0 | task 19408 | prompt eval time = 160.65 ms / 349 tokens ( 0.46 ms per token, 2172.49 tokens per second) 4.52.153.554 I slot print_timing: id 0 | task 19408 | eval time = 377.68 ms / 31 tokens ( 12.59 ms per token, 79.43 tokens per second) 4.52.153.555 I slot print_timing: id 0 | task 19408 | total time = 538.33 ms / 380 tokens 4.52.153.556 I slot print_timing: id 0 | task 19408 | graphs reused = 18358 4.52.153.557 I slot print_timing: id 0 | task 19408 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.153.585 I slot release: id 0 | task 19408 | stop processing: n_tokens = 411, truncated = 0 4.52.157.527 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 292045634 4.52.157.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.481 MiB) 4.52.247.452 I slot launch_slot_: id 0 | task 19442 | processing task, is_child = 0 4.55.415.589 I slot print_timing: id 0 | task 19442 | n_gen = 243, tg = 80.46 t/s, tg_3s = 80.79 t/s 4.58.416.684 I slot print_timing: id 0 | task 19442 | n_gen = 485, tg = 80.55 t/s, tg_3s = 80.64 t/s 5.01.421.322 I slot print_timing: id 0 | task 19442 | n_gen = 727, tg = 80.55 t/s, tg_3s = 80.54 t/s 5.04.433.249 I slot print_timing: id 0 | task 19442 | n_gen = 969, tg = 80.50 t/s, tg_3s = 80.35 t/s 5.05.116.319 I slot print_timing: id 0 | task 19442 | prompt eval time = 160.46 ms / 336 tokens ( 0.48 ms per token, 2094.02 tokens per second) 5.05.116.325 I slot print_timing: id 0 | task 19442 | eval time = 12708.39 ms / 1024 tokens ( 12.42 ms per token, 80.50 tokens per second) 5.05.116.327 I slot print_timing: id 0 | task 19442 | total time = 12868.85 ms / 1360 tokens 5.05.116.329 I slot print_timing: id 0 | task 19442 | graphs reused = 19376 5.05.116.329 I slot print_timing: id 0 | task 19442 | graph reallocs = 0 / 0 (same size) / (changed size) 5.05.116.358 I slot release: id 0 | task 19442 | stop processing: n_tokens = 1391, truncated = 0 5.05.141.279 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1391, t_last = 305008407 5.05.141.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.576 MiB) 5.05.242.929 I slot launch_slot_: id 0 | task 20469 | processing task, is_child = 0 5.08.415.209 I slot print_timing: id 0 | task 20469 | n_gen = 243, tg = 80.42 t/s, tg_3s = 80.75 t/s 5.10.403.034 I slot print_timing: id 0 | task 20469 | prompt eval time = 162.99 ms / 349 tokens ( 0.47 ms per token, 2141.30 tokens per second) 5.10.403.041 I slot print_timing: id 0 | task 20469 | eval time = 4997.10 ms / 403 tokens ( 12.43 ms per token, 80.45 tokens per second) 5.10.403.042 I slot print_timing: id 0 | task 20469 | total time = 5160.08 ms / 752 tokens 5.10.403.043 I slot print_timing: id 0 | task 20469 | graphs reused = 19775 5.10.403.044 I slot print_timing: id 0 | task 20469 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.403.076 I slot release: id 0 | task 20469 | stop processing: n_tokens = 783, truncated = 0 5.10.417.541 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 783, t_last = 310295125 5.10.417.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.951 MiB) 5.10.510.365 I slot launch_slot_: id 0 | task 20875 | processing task, is_child = 0 5.11.245.834 I slot print_timing: id 0 | task 20875 | prompt eval time = 160.55 ms / 349 tokens ( 0.46 ms per token, 2173.74 tokens per second) 5.11.245.839 I slot print_timing: id 0 | task 20875 | eval time = 574.90 ms / 47 tokens ( 12.50 ms per token, 80.01 tokens per second) 5.11.245.841 I slot print_timing: id 0 | task 20875 | total time = 735.45 ms / 396 tokens 5.11.245.841 I slot print_timing: id 0 | task 20875 | graphs reused = 19820 5.11.245.842 I slot print_timing: id 0 | task 20875 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.245.869 I slot release: id 0 | task 20875 | stop processing: n_tokens = 427, truncated = 0 5.11.272.738 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 311137918 5.11.272.783 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.326 MiB) 5.11.374.587 I slot launch_slot_: id 0 | task 20925 | processing task, is_child = 0 5.11.736.883 I slot print_timing: id 0 | task 20925 | prompt eval time = 172.22 ms / 385 tokens ( 0.45 ms per token, 2235.53 tokens per second) 5.11.736.889 I slot print_timing: id 0 | task 20925 | eval time = 190.06 ms / 16 tokens ( 12.67 ms per token, 78.92 tokens per second) 5.11.736.890 I slot print_timing: id 0 | task 20925 | total time = 362.28 ms / 401 tokens 5.11.736.890 I slot print_timing: id 0 | task 20925 | graphs reused = 19834 5.11.736.891 I slot print_timing: id 0 | task 20925 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.736.920 I slot release: id 0 | task 20925 | stop processing: n_tokens = 432, truncated = 0 5.11.763.780 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 311628969 5.11.763.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 5.11.856.595 I slot launch_slot_: id 0 | task 20944 | processing task, is_child = 0 5.12.718.015 I slot print_timing: id 0 | task 20944 | prompt eval time = 161.72 ms / 328 tokens ( 0.49 ms per token, 2028.25 tokens per second) 5.12.718.021 I slot print_timing: id 0 | task 20944 | eval time = 699.68 ms / 57 tokens ( 12.49 ms per token, 80.04 tokens per second) 5.12.718.022 I slot print_timing: id 0 | task 20944 | total time = 861.40 ms / 385 tokens 5.12.718.023 I slot print_timing: id 0 | task 20944 | graphs reused = 19889 5.12.718.024 I slot print_timing: id 0 | task 20944 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.718.053 I slot release: id 0 | task 20944 | stop processing: n_tokens = 416, truncated = 0